Paper Citation Record · LEDGER

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs

As of 23 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 2 inbound Pith citation observations for arXiv:2412.16974.

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

pith.paper-citation-record.v1
2412.16974 v1

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T05:58:47.845786Z

measured 49 of 49 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-22T01:19:00.268857Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T01:20:51.944045Z

Reference resolution

47 of 47 outbound references displayed

verified exact1
verified fuzzy3
unresolved43
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 415bb368-ae73-4b0c-9f91-12d8b4ee574d · outbound

This paper cites Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-11T05:58:48.517626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2f723bcc-5e0b-4061-bb80-8e5ad65cae2c · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs A General Language Assistant as a Laboratory for Alignment

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:46.718112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c321cdb-3502-4726-8c7d-e9a1d2d139a8 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:46.724041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5ebfa30-5335-4250-9fb9-e7f65f673208 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Constitutional AI: Harmlessness from AI Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:46.728472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5c01f6a-6782-41b4-b126-d7dafd5ede13 · outbound

This paper cites A unified taxonomy of harmful content.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs A unified taxonomy of harmful content

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:46.732208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ee5359f-6805-4140-8d39-29666863ae9e · outbound

This paper cites Information hazards: A typology of potential harms from knowledge.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Information hazards: A typology of potential harms from knowledge

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:58:48.609003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e3deb010-0cba-44ec-b3db-e02d6e300885 · outbound

This paper cites Deep Reinforcement Learning from Human Preferences.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Deep Reinforcement Learning from Human Preferences

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:58:48.543432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c16f6304-151f-48cc-a1eb-357e90be164f · outbound

This paper cites JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:46.743754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e096ccb-11f5-49cb-8127-375e8a945b15 · outbound

This paper cites Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:46.747261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6316c1e8-b068-4329-a185-52ee16a778f0 · outbound

This paper cites The Llama 3 Herd of Models.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs The Llama 3 Herd of Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:46.751649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f93b0e72-4068-4084-80af-7614f987af3b · outbound

This paper cites RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:46.832039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a0e703a-f44b-47ef-a833-7a9fc7a41a1a · outbound

This paper cites Improving alignment of dialogue agents via targeted human judgements.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Improving alignment of dialogue agents via targeted human judgements

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:46.954944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47694ab7-8434-432f-a732-d32674600a5f · outbound

This paper cites ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.006453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f792bc3-b2ad-405c-a89c-83342f6715b8 · outbound

This paper cites Parameter-Efficient Transfer Learning for NLP.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Parameter-Efficient Transfer Learning for NLP

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.010113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 120b379e-a521-4797-b5ce-c113137b7350 · outbound

This paper cites Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.014005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de8c7a63-d30e-4450-9c7f-3d5e70867b99 · outbound

This paper cites Beavertails: Towards improved safety alignment of llm via a human-preference dataset, 2023.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Beavertails: Towards improved safety alignment of llm via a human-preference dataset, 2023

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.018964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9b5ba2a-e286-4c71-8a01-45ade5ecd83f · outbound

This paper cites How can we know when language models know? on the calibration of language models for question answering.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs How can we know when language models know? on the calibration of language models for question answering

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.022320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90ad7620-3d9c-4bb5-b0fe-781b2272cba7 · outbound

This paper cites NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.026583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b679eb1e-a6af-4246-8abd-373faf51d28b · outbound

This paper cites SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.068771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 198ee191-dbd8-4346-be03-fbbedc16531f · outbound

This paper cites ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.152264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5edf7f31-a96c-4529-9744-e4cba6d49f36 · outbound

This paper cites Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.276350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3039cc7f-61f1-486a-8b95-ec772df7e680 · outbound

This paper cites Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.355053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dad2f2bb-285e-4ae2-aff3-5d44079fb857 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.359674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ca157f1-0b12-41dd-b9fd-f0be2384c948 · outbound

This paper cites UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.363796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b4a198e-3d01-452e-a5cb-12c5f2dcbb0a · outbound

This paper cites Rule Based Rewards for Language Model Safety.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Rule Based Rewards for Language Model Safety

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.367853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd4da059-4b99-4f46-a0a8-f60298839123 · outbound

This paper cites Crosslingual Generalization through Multitask Finetuning.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Crosslingual Generalization through Multitask Finetuning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.372522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5efb365-cde2-4cca-b350-82b67dce859e · outbound

This paper cites A Comprehensive Overview of Large Language Models.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs A Comprehensive Overview of Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.375962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e7b98eb-8ea3-4eaf-ac09-7ef48f516b0a · outbound

This paper cites Model spec, 5 2024.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Model spec, 5 2024

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:58:48.530851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 37522a85-fc18-4ede-a374-fccb088c0ca9 · outbound

This paper cites Training language models to follow instructions with human feedback.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Training language models to follow instructions with human feedback

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.383234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef368ef7-9cb0-404a-b61b-ee94084db68e · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.450308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f07b7287-65fd-4476-a87e-eb2c9188354e · outbound

This paper cites I'm Afraid I Can't Do That: Predicting Prompt Refusal in Black-Box Generative Language Models.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs I'm Afraid I Can't Do That: Predicting Prompt Refusal in Black-Box Generative Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.577628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13a117a8-50ce-4c0a-a611-4c302f667643 · outbound

This paper cites XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.656818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f80c1d25-cd01-4831-90aa-7295f79daefb · outbound

This paper cites Proximal Policy Optimization Algorithms.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Proximal Policy Optimization Algorithms

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.660911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9983772f-a372-4a91-94bb-3b5a5aac05f5 · outbound

This paper cites "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.664382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7739f1a3-c589-4f31-b004-e115abb647a1 · outbound

This paper cites Learning to summarize from human feedback.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Learning to summarize from human feedback

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.668432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95649f1d-3643-4c02-b9b5-e2adfc789d1b · outbound

This paper cites All Languages Matter: On the Multilingual Safety of Large Language Models.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs All Languages Matter: On the Multilingual Safety of Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.672211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 371fa624-1bd7-492b-8625-d337a844954c · outbound

This paper cites Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.676389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7137eb1c-fdac-46b1-8510-1a675799074a · outbound

This paper cites Smith, Daniel Khashabi, and Hannaneh Hajishirzi.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Smith, Daniel Khashabi, and Hannaneh Hajishirzi

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.680455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7596a72-84aa-4feb-bb5e-73f9ff413f89 · outbound

This paper cites Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.683998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1393e13-104e-4193-aa07-f2339d4e7367 · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Finetuned Language Models Are Zero-Shot Learners

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.687891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7386ce8-ace2-423e-a824-a96e41172a14 · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.691627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcb95f06-9061-4423-80a8-35073be2d2ba · outbound

This paper cites SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.761384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd6638d8-c1ca-4a13-8aae-b667bffed841 · outbound

This paper cites Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.829233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4963402-9065-42cb-9ab0-be3d7193a072 · outbound

This paper cites R-Tuning: Instructing Large Language Models to Say `I Don't Know'.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs R-Tuning: Instructing Large Language Models to Say `I Don't Know'

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.833858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d8b7914-3235-4b3d-bec7-58bcebcbf364 · outbound

This paper cites Instruction tuning for large language models: A survey, 2024 b.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Instruction tuning for large language models: A survey, 2024 b

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.837929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1611234-8817-437c-9df2-a37b07e1a696 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Fine-Tuning Language Models from Human Preferences

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.842057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49128758-1ec1-4825-9819-c663a818e4b1 · outbound

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

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T05:58:47.845786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 6794e616-2bcd-4901-b052-33f277cc3f4d · inbound

Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules cites this paper.

Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:28:09.935903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fded0e28-e891-4b7a-8aff-bed07bfe1418 · inbound

RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts cites this paper.

RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-22T01:20:51.947425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.