Paper Citation Record · LEDGER

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

As of 14 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 96 inbound Pith citation observations for arXiv:2310.11324.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2310.11324 v2

Coverage vector

measured 64 of 64 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-17T01:59:51.326493Z

measured 160 of 160 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 96 of 96 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:32:52.510712Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

64 of 64 outbound references displayed

verified exact10
verified fuzzy43
unresolved2
parse uncertain0
malformed identifier0
metadata mismatch9

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 23c5f13b-058f-4f8b-97de-a2411d423f31 · outbound

This paper cites Tweet: Susan & I found MMLU performance jump 6-10 points in the 40s by formatting multiple choice as (A) not A in MMLU (for internal model).

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Tweet: Susan & I found MMLU performance jump 6-10 points in the 40s by formatting multiple choice as (A) not A in MMLU (for internal model)

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.394625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 956be0df-66bb-4914-a0db-8cd4e7b5039f · outbound

This paper cites Falcon-40B : an open large language model with state-of-the-art performance.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Falcon-40B : an open large language model with state-of-the-art performance

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.501347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 925bbcdb-d037-43c3-b065-71c87e4f4038 · outbound

This paper cites An empirical evaluation of thompson sampling.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting An empirical evaluation of thompson sampling

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.503979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ba4e1fcf-f107-4b51-b6b3-062d01b12596 · outbound

This paper cites Better hypothesis testing for statistical machine translation: Controlling for optimizer instability.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Better hypothesis testing for statistical machine translation: Controlling for optimizer instability

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.506685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 88b0f953-5c8b-4220-9bcd-651eb1f61fe3 · outbound

This paper cites GPT 3.int8(): 8-bit matrix multiplication for transformers at scale.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting GPT 3.int8(): 8-bit matrix multiplication for transformers at scale

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.509487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 35fd58a4-464d-4701-b1f4-c35e5b1aa193 · outbound

This paper cites Openprompt: An open-source framework for prompt-learning.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Openprompt: An open-source framework for prompt-learning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.512258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ef7a012f-8209-4e1e-935a-00baa84995a4 · outbound

This paper cites Measuring and improving consistency in pretrained language models.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Measuring and improving consistency in pretrained language models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.515516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c5b09f3e-1956-450c-8160-8942eb53edba · outbound

This paper cites Deep reinforcement learning that matters.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Deep reinforcement learning that matters

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.519366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6c7f1cdf-d166-42c1-980b-8e8b26b7cfe1 · outbound

This paper cites Editing models with task arithmetic.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Editing models with task arithmetic

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.523190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation efb1adda-a288-4065-a733-9ed2f4c65e3c · outbound

This paper cites How can we know what language models know? Transactions of the Association for Computational Linguistics, 8: 0 423--438.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting How can we know what language models know? Transactions of the Association for Computational Linguistics, 8: 0 423--438

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.526558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c17940ac-8712-49eb-9a48-df739b684ee4 · outbound

This paper cites Asymptotically efficient adaptive allocation rules.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Asymptotically efficient adaptive allocation rules

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.529807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 69a1127a-7e13-4c0a-badc-649939be276a · outbound

This paper cites The power of scale for parameter-efficient prompt tuning.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting The power of scale for parameter-efficient prompt tuning

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.533654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1b610d35-481b-4300-8abb-3812474c5d8d · outbound

This paper cites Rouge: A package for automatic evaluation of summaries.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Rouge: A package for automatic evaluation of summaries

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.537693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1f5438eb-dfa8-414f-86d3-4f75dddc46a1 · outbound

This paper cites What makes chain-of-thought prompting effective? a counterfactual study.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting What makes chain-of-thought prompting effective? a counterfactual study

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.541594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9e5056de-a469-4e7b-802e-28445a228263 · outbound

This paper cites Stereoset: Measuring stereotypical bias in pretrained language models.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Stereoset: Measuring stereotypical bias in pretrained language models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.544935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 67abd06c-7927-4565-bdc4-01521636eed4 · outbound

This paper cites Learning how to ask: Querying lms with mixtures of soft prompts.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Learning how to ask: Querying lms with mixtures of soft prompts

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.547957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 87eabb56-a08b-463f-84ba-6b8cc280e469 · outbound

This paper cites Self-diagnosis and self-debiasing: A proposal for reducing corpus-based bias in nlp.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Self-diagnosis and self-debiasing: A proposal for reducing corpus-based bias in nlp

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.551285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6bcac65a-229f-407b-a575-735fcb99ab1b · outbound

This paper cites Chatgpt: Optimizing language models for dialogue.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Chatgpt: Optimizing language models for dialogue

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.554500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ce4cb433-8914-4664-9e4b-0cd8553c6402 · outbound

This paper cites Bertscore: Evaluating text generation with bert.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Bertscore: Evaluating text generation with bert

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.557702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 363ad71d-9efc-4221-a71f-71beafb4a411 · outbound

This paper cites Large language models are human-level prompt engineers.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Large language models are human-level prompt engineers

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.428661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 303e6923-59d2-4188-9afa-ecef67cd933b · outbound

This paper cites Findings of the Association for Computational Linguistics: EMNLP 2023 , pages=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Findings of the Association for Computational Linguistics: EMNLP 2023 , pages=

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.431448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ce95afe9-39b8-41aa-bf58-377ab12a4698 · outbound

This paper cites Scaling Learning Algorithms Towards.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Scaling Learning Algorithms Towards

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.434692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3fdc71a9-eb1c-48dd-9eaf-2490eeefec66 · outbound

This paper cites and Osindero, Simon and Teh, Yee Whye , journal =.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting and Osindero, Simon and Teh, Yee Whye , journal =

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.437652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7cb0a65f-d2bb-4230-aa33-fabbc7b8dbdd · outbound

This paper cites 2016 , publisher=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting 2016 , publisher=

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.440521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a894853f-7809-492e-8cc1-6e3d66184bc2 · outbound

This paper cites Transactions of the Association for Computational Linguistics , volume=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Transactions of the Association for Computational Linguistics , volume=

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.443192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation adddd939-ed1f-43d7-af5e-356bd620117d · outbound

This paper cites Super- N atural I nstructions: Generalization via declarative instructions on 1600+ NLP tasks.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Super- N atural I nstructions: Generalization via declarative instructions on 1600+ NLP tasks

Reference 43

Resolution: verified exact; doi, observed 2026-05-17T01:59:51.384220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6d3acaeb-17d6-4dd3-89c7-43c915e926ea · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 44

Resolution: metadata mismatch; local_arxiv, observed 2026-05-17T01:59:51.411132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e7963705-ba5a-4820-af5b-668668322802 · outbound

This paper cites an unresolved cited work.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-05-17T01:59:51.445968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0fdbc677-f88c-4be8-8d5e-7376cb06b0cb · outbound

This paper cites Reframing Instructional Prompts to GPTk's Language.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Reframing Instructional Prompts to GPTk's Language

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T01:59:51.407613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0b22b42e-7e46-489c-b79e-0ab25d634b23 · outbound

This paper cites Transactions of the Association for Computational Linguistics , volume=.

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.449067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4e1ed639-7176-459f-a20c-b2f7e260e0a3 · outbound

This paper cites and Wallace, Eric and Singh, Sameer.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting and Wallace, Eric and Singh, Sameer

Reference 48

Resolution: verified exact; doi, observed 2026-05-17T01:59:51.386958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9332d508-fd90-48aa-8f5c-5c72f609a9de · outbound

This paper cites RLP rompt: Optimizing Discrete Text Prompts with Reinforcement Learning.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting RLP rompt: Optimizing Discrete Text Prompts with Reinforcement Learning

Reference 49

Resolution: verified exact; doi, observed 2026-05-17T01:59:51.361456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2d1f930c-6029-4fd1-abd4-8bb73c703fcf · outbound

This paper cites G r IPS : Gradient-free, Edit-based Instruction Search for Prompting Large Language Models.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting G r IPS : Gradient-free, Edit-based Instruction Search for Prompting Large Language Models

Reference 50

Resolution: verified exact; doi, observed 2026-05-17T01:59:51.367718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 684c532d-f3c3-412c-aee9-67edfa5e69c0 · outbound

This paper cites Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.425681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7802663b-0457-45e6-aaf6-30dfdac66826 · outbound

This paper cites The Eleventh International Conference on Learning Representations , year=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting The Eleventh International Conference on Learning Representations , year=

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.452037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5ac2f298-efaf-462f-9ad2-c7d11eb7e95e · outbound

This paper cites Automatic Prompt Optimization with "Gradient Descent" and Beam Search.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.390802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cdd0a501-f844-4ed7-95e0-796f3a5ed4c0 · outbound

This paper cites Text summarization branches out , pages=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Text summarization branches out , pages=

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.455527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0db92237-9bae-4670-a5f5-a1837037446d · outbound

This paper cites International Conference on Learning Representations , year=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting International Conference on Learning Representations , year=

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.458580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 34689bb0-5418-4fde-b316-dc369ef0ed53 · outbound

This paper cites The Eleventh International Conference on Learning Representations , year=.

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.461095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7acd681a-a8bc-45a2-b6ed-a7c4ae282724 · outbound

This paper cites 2023 , url =.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting 2023 , url =

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.463495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3597a8de-b7d7-4221-bad5-b1edc0fab879 · outbound

This paper cites 2023 , eprint=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting 2023 , eprint=

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.465742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9079ed20-f698-4c86-9b07-489d1b1d3578 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 59

Resolution: metadata mismatch; local_arxiv, observed 2026-05-17T01:59:51.414513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4b9b33c4-422a-41a7-9277-514c541c5a89 · outbound

This paper cites Jailbroken: How Does LLM Safety Training Fail?.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Jailbroken: How Does LLM Safety Training Fail?

Reference 60

Resolution: metadata mismatch; local_arxiv, observed 2026-05-17T01:59:51.421696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e0f1cf4c-2221-4853-9611-d9eee7638c10 · outbound

This paper cites 2022 , url=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting 2022 , url=

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.468076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b62c89cf-8186-4d10-b394-f6b6d82c0e14 · outbound

This paper cites Advances in neural information processing systems , volume=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Advances in neural information processing systems , volume=

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.470604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ed0459fa-53df-4574-84c7-53b74c5b28bc · outbound

This paper cites Advances in applied mathematics , volume=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Advances in applied mathematics , volume=

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.473063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 48b41ed1-527d-43bd-bf2c-c133a2a03a5d · outbound

This paper cites A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT

Reference 64

Resolution: metadata mismatch; local_arxiv, observed 2026-05-17T01:59:51.398030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 79ef4430-c6ac-46b7-b90f-63670cb02eee · outbound

This paper cites Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity

Reference 65

Resolution: verified exact; doi, observed 2026-05-17T01:59:51.377945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fa491dbd-8986-483e-8de1-53b530d9f23e · outbound

This paper cites Demystifying Prompts in Language Models via Perplexity Estimation.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Demystifying Prompts in Language Models via Perplexity Estimation

Reference 66

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T01:59:51.403617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c09083b8-870b-4ffb-9aee-d26dcf3e37d7 · outbound

This paper cites doi: 10.18653/v1/2021.acl-long.295.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting doi: 10.18653/v1/2021.acl-long.295

Reference 67

Resolution: metadata mismatch; doi, observed 2026-05-17T01:59:51.381003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f0463af4-f301-44b1-8e27-58c4ebc9fd6b · outbound

This paper cites and Levy, Omer.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting and Levy, Omer

Reference 68

Resolution: verified exact; doi, observed 2026-05-17T01:59:51.370516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d7bd6c92-6451-4ae4-85c8-20ad0c8e3e11 · outbound

This paper cites Chen and C.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Chen and C

Reference 69

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T01:59:51.374277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 277fac3e-bce9-4b1f-bc44-e224a5b0c1be · outbound

This paper cites an unresolved cited work.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-05-17T01:59:51.475332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6315a095-6442-4f59-8434-5c95ad579103 · outbound

This paper cites Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) , year=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) , year=

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.477813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 63a03461-8ef6-4f3b-9801-72fd56b21afb · outbound

This paper cites Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations , pages=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations , pages=

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.480294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f0fa1666-343a-4a81-94c1-afc124fdc093 · outbound

This paper cites Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing , pages=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.483065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 06807b0d-c111-442f-9c49-bfc1f1dca216 · outbound

This paper cites Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts

Reference 74

Resolution: verified exact; doi, observed 2026-05-17T01:59:51.365010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ac4ccb65-6b8b-41a3-83d2-722b6f0c8d2b · outbound

This paper cites Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing , pages=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.485685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5cda8762-5e00-4b05-bfa4-73a7a1c30a49 · outbound

This paper cites Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies , pages=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies , pages=

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.488168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 62ee2e47-b803-4397-ae12-dfa2aa8d5498 · outbound

This paper cites Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control

Reference 77

Resolution: metadata mismatch; local_arxiv, observed 2026-05-17T01:59:51.418148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 90da363f-d2d8-4b37-b585-cfe12678bc2a · outbound

This paper cites OpenAI blog , year=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting OpenAI blog , year=

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.490490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 79f94082-5c5e-4783-a0f5-42fabe4a2263 · outbound

This paper cites Transactions of the Association for Computational Linguistics , volume=.

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.492948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1d185803-b062-4568-92b2-ee65b70b3a8a · outbound

This paper cites Proceedings of the AAAI conference on artificial intelligence , volume=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Proceedings of the AAAI conference on artificial intelligence , volume=

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.495994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 017a4e09-2529-4a05-a318-df7e76e82b77 · outbound

This paper cites 2023 , booktitle=.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting 2023 , booktitle=

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:59:51.498435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation 67d1c560-d29b-4c70-b960-e933eb8b09ac · inbound

Lessons from the Trenches on Reproducible Evaluation of Language Models cites this paper.

Lessons from the Trenches on Reproducible Evaluation of Language Models Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 104

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation afc502ba-3a02-4d8f-978b-05972e225180 · inbound

Leveraging LLMs for Predictive Insights in Food Policy and Behavioral Interventions cites this paper.

Leveraging LLMs for Predictive Insights in Food Policy and Behavioral Interventions Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-12T21:35:15.564134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf5aaaec-a456-484e-9538-44747de18621 · inbound

Does Prompt Formatting Have Any Impact on LLM Performance? cites this paper.

Does Prompt Formatting Have Any Impact on LLM Performance? Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T19:38:26.789374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b23bf9eb-c0aa-4a52-96a4-9573e21b26b9 · inbound

BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices cites this paper.

BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-12T17:01:31.658676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a4fd0ef-9e60-46d5-a808-f148bfbb1e3f · inbound

AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations cites this paper.

AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-12T16:27:47.890701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cd638b4-c102-494e-97bc-47d81fd50750 · inbound

InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks cites this paper.

InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-12T11:29:29.554565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49783f9b-3fb7-4782-bb87-16bbfa5ff718 · inbound

The broader spectrum of in-context learning cites this paper.

The broader spectrum of in-context learning Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-11T22:10:22.937583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54eaeb8b-5944-4991-9dbb-49cb7d52c8a9 · inbound

Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review cites this paper.

Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 144

Resolution: unresolved; no resolver link, observed 2026-08-10T17:06:55.633108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82f21333-e037-4555-80b5-9af74df1f2ba · inbound

Normative Evaluation of Large Language Models with Everyday Moral Dilemmas cites this paper.

Normative Evaluation of Large Language Models with Everyday Moral Dilemmas Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-10T00:49:57.082783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0441053-09e6-4cd6-ab56-93da98c43b82 · inbound

CodeSCM: Causal Analysis for Multi-Modal Code Generation cites this paper.

CodeSCM: Causal Analysis for Multi-Modal Code Generation Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:13.553448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11dfe6a2-4267-4f6a-ade1-3359f6563496 · inbound

Benchmarking Prompt Sensitivity in Large Language Models cites this paper.

Benchmarking Prompt Sensitivity in Large Language Models Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-08T16:55:45.540970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fff5e99a-28a3-401f-9e05-938aaa4da2a4 · inbound

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs cites this paper.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-08T00:04:57.434528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e07dffd-368e-47e8-9de9-c952a1b2c84a · inbound

Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions cites this paper.

Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-05-23T03:02:26.773428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d4d06f39-afbc-4e11-947d-80b83b9585f3 · inbound

Collaboration among Multiple Large Language Models for Medical Question Answering cites this paper.

Collaboration among Multiple Large Language Models for Medical Question Answering Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:02:08.057788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7b88fb4-20ef-490b-a7e5-975aef909afc · inbound

Existing Large Language Model Unlearning Evaluations Are Inconclusive cites this paper.

Existing Large Language Model Unlearning Evaluations Are Inconclusive Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T12:05:56.757190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cbae61c-9af0-476c-8de6-d50f1e5c1aa3 · inbound

A Multimodal, Multilingual, and Multidimensional Pipeline for Fine-grained Crowdsourcing Earthquake Damage Evaluation cites this paper.

A Multimodal, Multilingual, and Multidimensional Pipeline for Fine-grained Crowdsourcing Earthquake Damage Evaluation Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:08:12.470417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32d913c0-1673-4981-82e1-4f9a59691a1f · inbound

More or Less Wrong: A Benchmark for Directional Bias in LLM Comparative Reasoning cites this paper.

More or Less Wrong: A Benchmark for Directional Bias in LLM Comparative Reasoning Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T10:59:06.932061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45ab169e-069f-4672-a7ee-8567bcce31df · inbound

Understanding and Meeting Practitioner Needs When Measuring Representational Harms Caused by LLM-Based Systems cites this paper.

Understanding and Meeting Practitioner Needs When Measuring Representational Harms Caused by LLM-Based Systems Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:03.052746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34196dfb-50c7-4c67-a110-faae8e7dc90c · inbound

From Prompts to Constructs: A Dual-Validity Framework for LLM Research in Psychology cites this paper.

From Prompts to Constructs: A Dual-Validity Framework for LLM Research in Psychology Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:28.044768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fab458f-9a4d-40f5-b211-9ed2da36fff3 · inbound

Requirements Elicitation Follow-Up Question Generation cites this paper.

Requirements Elicitation Follow-Up Question Generation Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T20:23:07.707797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a2ea975-db5b-4873-ae31-2c52ef77f146 · inbound

PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation cites this paper.

PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-19T03:47:02.410931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b6dd6aea-528c-453c-bae2-a93bc18b02e6 · inbound

Understanding Human Limits in Pattern Recognition: A Computational Model of Sequential Reasoning in Rock, Paper, Scissors cites this paper.

Understanding Human Limits in Pattern Recognition: A Computational Model of Sequential Reasoning in Rock, Paper, Scissors Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T14:26:03.490201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6230737b-69d8-4d1e-8bf6-a0bf9e508377 · inbound

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis cites this paper.

Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T17:13:52.950973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 950659b2-ed32-4383-a1da-4e75ab68be5f · inbound

Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs cites this paper.

Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-05T12:17:20.371226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c0c6ae2-382e-4d24-b1ab-c7c9c75339c6 · inbound

No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models cites this paper.

No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T21:22:14.357858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8094e4a3-c2f5-4e28-b429-c33515ecf71b · inbound

From scratch to silver: Creating trustworthy training data for patent-SDG classification using Large Language Models cites this paper.

From scratch to silver: Creating trustworthy training data for patent-SDG classification using Large Language Models Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-04T19:27:04.897757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b551cc06-294f-4c30-a9f9-467c782b935b · inbound

Discrimination by LLMs: Cross-lingual Bias Assessment and Mitigation in Decision-Making and Summarisation cites this paper.

Discrimination by LLMs: Cross-lingual Bias Assessment and Mitigation in Decision-Making and Summarisation Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T20:19:50.468699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1048b3db-c417-4803-8f34-526566bf1e09 · inbound

Discrimination by LLMs: Cross-lingual Bias Assessment and Mitigation in Decision-Making and Summarisation cites this paper.

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T20:19:50.473280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0196a771-86c1-43c1-b180-a3060c8fcad1 · inbound

Position: AI Evaluations Should be Grounded on a Theory of Capability cites this paper.

Position: AI Evaluations Should be Grounded on a Theory of Capability Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-05-21T22:00:41.479428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f113b980-247b-40cb-9faf-2fa1e4ab22bb · inbound

Activation Steering with a Feedback Controller cites this paper.

Activation Steering with a Feedback Controller Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-21T21:50:41.383188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a3f56d2a-92ff-4ca4-95a4-967095642230 · inbound

RegCheck: A tool for structured comparisons between study registrations and papers cites this paper.

RegCheck: A tool for structured comparisons between study registrations and papers Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T09:36:34.579749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb725fc7-ab55-474c-8cc3-d4fbcb21f1dc · inbound

RegCheck: A tool for structured comparisons between study registrations and papers cites this paper.

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T09:36:34.417517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0b70b9e-7ec7-4425-9461-f809d8b0a067 · inbound

Framing Instability in LLM Ethical Stance: Auditing Negation Sensitivity in Moral Dilemmas cites this paper.

Framing Instability in LLM Ethical Stance: Auditing Negation Sensitivity in Moral Dilemmas Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T07:03:14.824744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59a49e8a-dbed-4b47-8ff8-9afa1e692aa5 · inbound

Visual Persuasion: What Influences Decisions of Vision-Language Models? cites this paper.

Visual Persuasion: What Influences Decisions of Vision-Language Models? Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T23:00:27.287919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5639a345-b6f2-4d0f-a369-79ee60fb985f · inbound

Collective AI can amplify tiny perturbations into divergent decisions cites this paper.

Collective AI can amplify tiny perturbations into divergent decisions Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c4363e52-b8a2-456a-8a84-b2de1811b75a · inbound

Causal Evidence that Language Models use Confidence to Drive Behavior cites this paper.

Causal Evidence that Language Models use Confidence to Drive Behavior Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-21T09:44:05.678228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f0ab09b1-d23b-4100-a869-6a77e807a213 · inbound

Dual Implications of Quark Mass Hierarchies to Flavor Structure cites this paper.

Dual Implications of Quark Mass Hierarchies to Flavor Structure Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-13T13:46:54.451163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5077a94-b1f6-4337-b9bb-dd86afecd2eb · inbound

Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens cites this paper.

Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6a0da57e-c6c1-45ef-b2e3-5dade4b334c6 · inbound

The Cartesian Cut in Agentic AI cites this paper.

The Cartesian Cut in Agentic AI Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 58

Resolution: malformed identifier; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4e800469-e96b-4d01-974b-b63e89638940 · inbound

Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees cites this paper.

Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fd3276a5-c025-4ae0-8bfe-3e05b32ad1b8 · inbound

The PICCO Framework for Large Language Model Prompting: A Taxonomy and Reference Architecture for Prompt Structure cites this paper.

The PICCO Framework for Large Language Model Prompting: A Taxonomy and Reference Architecture for Prompt Structure Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fd771154-d352-40ab-a386-13d231096e1b · inbound

SPAGBias: Uncovering and Tracing Structured Spatial Gender Bias in Large Language Models cites this paper.

SPAGBias: Uncovering and Tracing Structured Spatial Gender Bias in Large Language Models Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b656be60-9453-48e1-b04d-c00fc60baf97 · inbound

Compared to What? Baselines and Metrics for Counterfactual Prompting cites this paper.

Compared to What? Baselines and Metrics for Counterfactual Prompting Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 54

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b3540b05-1e28-4ba6-9009-187f14869d22 · inbound

What Single-Prompt Accuracy Misses: A Multi-Variant Reliability Audit of Language Models cites this paper.

What Single-Prompt Accuracy Misses: A Multi-Variant Reliability Audit of Language Models Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9b7c6f9c-0405-434b-a17f-816941b1d01a · inbound

Benchmarking Local Language Models for Social Robots using Edge Devices cites this paper.

Benchmarking Local Language Models for Social Robots using Edge Devices Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 98600158-a739-4ef0-b0b4-de4212556679 · inbound

Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs cites this paper.

Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 83ff963b-d838-4c2d-a198-21f2622ffc4f · inbound

Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs cites this paper.

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 975fbeb2-490a-4282-bb4a-d5cd8db7c00f · inbound

Beyond Accuracy: Policy Invariance as a Reliability Test for LLM Safety Judges cites this paper.

Beyond Accuracy: Policy Invariance as a Reliability Test for LLM Safety Judges Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b6f3d18d-dbf1-4f98-a18e-3f42002bc3b8 · inbound

Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity cites this paper.

Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 34ae1dde-d9bf-479c-bce8-692524314ae3 · inbound

Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML cites this paper.

Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 293

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f333364e-a655-438f-9a68-0ccb8934eee6 · inbound

The Text Uncanny Valley: Non-Monotonic Performance Degradation in LLM Information Retrieval cites this paper.

The Text Uncanny Valley: Non-Monotonic Performance Degradation in LLM Information Retrieval Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c80d12c3-6a2f-40a8-a7f5-cfb844a17bd0 · inbound

CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios cites this paper.

CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b4349365-f316-4c16-aa26-d9233aba4688 · inbound

CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging cites this paper.

CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.558892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 526d97db-3377-46d5-baa0-7ba430a84b00 · inbound

CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging cites this paper.

CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:35:46.961576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 49678d8d-4a34-418b-a548-c911ef1878f8 · inbound

Beyond the Cartesian Illusion: Testing Two-Stage Multi-Modal Theory of Mind under Perceptual Bottlenecks cites this paper.

Beyond the Cartesian Illusion: Testing Two-Stage Multi-Modal Theory of Mind under Perceptual Bottlenecks Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:13:11.910514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3355f211-f632-46a9-b56f-75db36161e2f · inbound

Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits cites this paper.

Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 63

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:43:19.588773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 98ca3752-a808-47be-b31d-4478a0c7e66a · inbound

Towards Context-Invariant Safety Alignment for Large Language Models cites this paper.

Towards Context-Invariant Safety Alignment for Large Language Models Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 46

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T05:39:40.847530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dd1d57e0-4ee4-4a65-90ef-28dd879c1439 · inbound

SafetyRepro: Configuration-Conditional Rank Instability on Alignment Benchmarks cites this paper.

SafetyRepro: Configuration-Conditional Rank Instability on Alignment Benchmarks Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-06-29T22:54:00.992662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2a250451-02d6-4609-8150-551b576494b5 · inbound

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline cites this paper.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-06-30T14:54:45.706466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 65addb7c-8ece-4002-9a36-c4a24c3c2aff · inbound

Chain-based Adaptive Reconfiguration Over Lattices for Hallucination Reduction cites this paper.

Chain-based Adaptive Reconfiguration Over Lattices for Hallucination Reduction Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T18:13:48.306109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 532c76cf-ba79-4c40-ad63-cc7413ad183f · inbound

Specialty-Specific Medical Language Model for Immune-Mediated Diseases cites this paper.

Specialty-Specific Medical Language Model for Immune-Mediated Diseases Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-12T22:27:01.885350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b750e918-9a7b-430d-a5cb-c5eef6908d31 · inbound

How Consistent Are LLM Agents? Measuring Behavioral Reproducibility in Multi-Step Tool-Calling Pipelines cites this paper.

How Consistent Are LLM Agents? Measuring Behavioral Reproducibility in Multi-Step Tool-Calling Pipelines Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-04T21:40:08.966556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4c8908a7-5104-4e75-b152-b9504f050c72 · inbound

Mind Your Tone: Does Tone Alter LLM Performance? cites this paper.

Mind Your Tone: Does Tone Alter LLM Performance? Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T12:23:23.829759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2a0ffda8-a8a4-46bc-abc3-8f524e2a89ca · inbound

Persona Conditioning of Brand Recommendations in Retrieval-Augmented Commercial Chat: A Prominence-Stratified Cross-Provider Audit cites this paper.

Persona Conditioning of Brand Recommendations in Retrieval-Augmented Commercial Chat: A Prominence-Stratified Cross-Provider Audit Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-06-29T07:23:12.704384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f2bf329c-cc47-4e49-aec3-76de5a68e488 · inbound

Same Patient, Different Words, Different Diagnosis? Evaluating Semantic Stability in Clinical LLMs cites this paper.

Same Patient, Different Words, Different Diagnosis? Evaluating Semantic Stability in Clinical LLMs Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-06-29T07:23:13.270260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 35f46b7d-ee0d-45b8-b27a-509280c3a4ee · inbound

On the impact of retrieved content representations in RAG Pipelines cites this paper.

On the impact of retrieved content representations in RAG Pipelines Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T20:16:12.164754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9be348f7-4089-4696-8886-d694bcc3defb · inbound

Consistency Training Can Entrench Misalignment cites this paper.

Consistency Training Can Entrench Misalignment Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 49

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T03:26:28.642293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2b1fce16-aaa5-425c-bdd7-c036efbc2c5f · inbound

AIP: A Graph Representation for Learning and Governing Agent Skills cites this paper.

AIP: A Graph Representation for Learning and Governing Agent Skills Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-02T08:36:47.780631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 15aecd79-a8fd-4cdd-8e56-ab18ad9839f6 · inbound

Stability vs. Manipulability: Evaluating Robustness Under Post-Decision Interaction in LLM Judges cites this paper.

Stability vs. Manipulability: Evaluating Robustness Under Post-Decision Interaction in LLM Judges Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 67

Resolution: verified exact; local_arxiv, observed 2026-07-02T08:36:47.667751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 484c52d7-3061-452d-9891-7327bd6971d1 · inbound

Self-Harness: Harnesses That Improve Themselves cites this paper.

Self-Harness: Harnesses That Improve Themselves Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-07-03T01:37:30.768446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 925b5beb-4f5a-4615-89d0-f13eb0d0586b · inbound

Are We Evaluating Knowledge or Phrasing? Mitigating MCQA Sensitivity with ParaEval cites this paper.

Are We Evaluating Knowledge or Phrasing? Mitigating MCQA Sensitivity with ParaEval Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-03T05:27:40.336372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation abd1163d-84b0-4ee9-bd69-342245e3dc8a · inbound

Preregistration for Experiments with AI Agents cites this paper.

Preregistration for Experiments with AI Agents Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 60

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T00:15:08.983043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 61da2415-daca-4f13-9f56-221c666c47ee · inbound

To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG cites this paper.

To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T18:40:02.339892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d007a58f-9e84-473f-97f8-cc5aed4a3759 · inbound

Instruction Bleed: Cross-Module Interference in Prompt-Composed Agentic Systems cites this paper.

Instruction Bleed: Cross-Module Interference in Prompt-Composed Agentic Systems Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-04T15:19:56.816194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 26506fa3-9f47-42c5-a0e4-2f67a613a2a0 · inbound

A Deterministic Control Plane for LLM Coding Agents cites this paper.

A Deterministic Control Plane for LLM Coding Agents Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-07-04T14:19:54.749800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 477d1fd4-b47e-44a5-b56a-38f93edfa261 · inbound

Towards Physical Intuitions for Alignment Dynamics: A Case Study With Randomness Crystallization cites this paper.

Towards Physical Intuitions for Alignment Dynamics: A Case Study With Randomness Crystallization Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T06:44:19.133463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1b62b622-50c2-4937-8790-2dcd97e20740 · inbound

Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models cites this paper.

Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-07-01T11:05:42.229723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b1b818aa-b07c-4c93-9dc7-786f9c5ae973 · inbound

A Penny for Your Prompts: Experiments Detecting and Mitigating LLM Usage by Survey Respondents cites this paper.

A Penny for Your Prompts: Experiments Detecting and Mitigating LLM Usage by Survey Respondents Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 65

Resolution: verified exact; local_arxiv, observed 2026-07-02T07:06:43.608084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 72628e34-64c9-48b3-888c-2d2ed69436c4 · inbound

Persona Non Grata: LLM Persona-Driven Generations in MCQA are Unstable in Distinct Dimensions cites this paper.

Persona Non Grata: LLM Persona-Driven Generations in MCQA are Unstable in Distinct Dimensions Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 43

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T13:06:58.396919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 64b3a29c-8133-43ca-8f98-9fcec3499afc · inbound

The Powerless Noise: How Experimental Settings Shape the Reported Power of Noise cites this paper.

The Powerless Noise: How Experimental Settings Shape the Reported Power of Noise Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-12T01:10:52.578408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6331b2e4-56c8-4ba6-82e6-43216ff0e9a5 · inbound

The Powerless Noise: How Experimental Settings Shape the Reported Power of Noise cites this paper.

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-13T07:04:18.645464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8aa52b9-50b7-4857-ba42-2e5c7aaf4568 · inbound

Efficient Safety Alignment of Language Models via Latent Personality Traits cites this paper.

Efficient Safety Alignment of Language Models via Latent Personality Traits Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.131028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f939d13c-bfd1-46c4-a7d4-751fde27759e · inbound

Format Sensitivity Index: Token-Controlled Prompt Wrapper Robustness and Schema Compliance in LLM Benchmarking cites this paper.

Format Sensitivity Index: Token-Controlled Prompt Wrapper Robustness and Schema Compliance in LLM Benchmarking Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-14T19:17:45.652076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d107bd2-1d3c-4cd8-8594-ed31dca207d5 · inbound

When Counterbalancing Hides the Bias: Access-Conditioned Position Lock in Forced-Choice LLM Evaluation cites this paper.

When Counterbalancing Hides the Bias: Access-Conditioned Position Lock in Forced-Choice LLM Evaluation Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-14T13:32:31.523845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4252f286-08e7-4cb1-8455-ed83ca30c39f · inbound

Linear representations of grammaticality in neural language models cites this paper.

Linear representations of grammaticality in neural language models Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 202

Resolution: unresolved; no resolver link, observed 2026-08-01T23:59:51.912910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e26db494-ebb4-4594-b5bd-f2c979823a99 · inbound

Structured Output Collapses Answer Diversity Across 44 Language Models cites this paper.

Structured Output Collapses Answer Diversity Across 44 Language Models Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T15:23:45.126518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a6c7e48-a5a8-457c-95de-9d0822855397 · inbound

Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models cites this paper.

Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T13:01:01.724152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d850a5a-62e4-4273-8f1d-1f3e1059691d · inbound

A Knowledge-Injection Framework for Zero-Shot Adaptation of LLMs to Delirium Prediction cites this paper.

A Knowledge-Injection Framework for Zero-Shot Adaptation of LLMs to Delirium Prediction Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T13:59:21.524288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d827d14-b1c1-4bd3-928a-5498c3224a70 · inbound

Reexamining zero-shot summarization: Empirical investigation of trustworthiness of LLM-summarizers cites this paper.

Reexamining zero-shot summarization: Empirical investigation of trustworthiness of LLM-summarizers Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T08:46:15.357112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b5a835c-c89d-4baa-bb83-3058e788e72b · inbound

Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy cites this paper.

Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T13:46:09.599956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c0b3f9e-5023-42cf-bfe0-6d65e5718c24 · inbound

Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity cites this paper.

Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T00:48:49.223511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b8dfe7b-3e8f-4616-9f54-dc2a0ac0623b · inbound

Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents cites this paper.

Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 138

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:15.005783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb688394-056d-41d5-aaf1-007eadd68b80 · inbound

Same physical state, different collective dynamics: state encodings select synchronization outcomes in language-model agents cites this paper.

Same physical state, different collective dynamics: state encodings select synchronization outcomes in language-model agents Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T17:33:56.227086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdbbb002-5899-4cc3-8b58-02836ac5f396 · inbound

Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation cites this paper.

Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T00:52:42.047818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6de43ecb-a9bc-44da-99b5-bed25974c9c2 · inbound

Actions Speak Louder than Words: Measuring Cross-Lingual Policy Retention in Tool-Using Agents cites this paper.

Actions Speak Louder than Words: Measuring Cross-Lingual Policy Retention in Tool-Using Agents Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T06:04:17.071359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bb96473-236a-497f-ba68-8dd57ed9a617 · inbound

QuoteBench: How Matched Scores Can Hide Command-Path Failures cites this paper.

QuoteBench: How Matched Scores Can Hide Command-Path Failures Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-14T04:32:52.510712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.