Paper Citation Record · LEDGER

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation

As of 8 August 2026, this Paper Citation Record lists 100 of 102 outbound references and 2 inbound Pith citation observations for arXiv:2602.11908.

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

pith.paper-citation-record.v1
2602.11908 v3

Coverage vector

measured 100 of 102 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T00:03:31.683006Z

measured 102 of 102 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-20T23:56:44.979471Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-20T23:59:15.248753Z

Reference resolution

100 of 102 outbound references displayed

verified exact1
verified fuzzy0
unresolved96
parse uncertain0
malformed identifier3
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1bf1bff5-6fc0-441d-8fc5-b655e24efdae · outbound

This paper cites Towards a Human-like Open-Domain Chatbot.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Towards a Human-like Open-Domain Chatbot

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:18.159203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d42595d8-6316-4003-a61f-f0e44f1310fc · outbound

This paper cites A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:18.276169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2be8f48b-ec61-42f6-accb-df1f2ee1da36 · outbound

This paper cites Introducing the claude 3 model family.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Introducing the claude 3 model family

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:18.391062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63fb5a86-0296-4ccd-aded-94fa500e3f10 · outbound

This paper cites Semantic information.British Journal for the Philosophy of Science, 4(14):147–157, 1953.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Semantic information.British Journal for the Philosophy of Science, 4(14):147–157, 1953

Reference 4

Resolution: malformed identifier; doi_truncated, observed 2026-08-03T00:03:37.212558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0cfb03ed-6361-4934-8fb3-2aa4055473cc · outbound

This paper cites Synthese Library.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Synthese Library

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:18.551481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 648a5623-6eca-40cc-a92f-ff7a0eecd95b · outbound

This paper cites DeepSeek-V3 Technical Report.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation DeepSeek-V3 Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:18.642129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdbe0663-d3a9-4b7b-9375-4dd9c5a6fff7 · outbound

This paper cites On the founda- tions of noise-free selective classification.J.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation On the founda- tions of noise-free selective classification.J

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:18.731927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b897719-37c9-497f-8cd3-9322676b34df · outbound

This paper cites Lm-polygraph: Un- certainty estimation for language models.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Lm-polygraph: Un- certainty estimation for language models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:18.855499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e32955a-5b45-49a8-9c8a-e8ec615464d0 · outbound

This paper cites Fact-checking the out- put of large language models via token-level uncer- tainty quantification.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Fact-checking the out- put of large language models via token-level uncer- tainty quantification

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:18.986476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c901e001-d035-4f74-97fd-4575528a5066 · outbound

This paper cites Don’t hallucinate, abstain: Identifying LLM knowl- edge gaps via multi-llm collaboration.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Don’t hallucinate, abstain: Identifying LLM knowl- edge gaps via multi-llm collaboration

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:19.138224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08176e05-1956-4d95-8ac6-e7aff94de8c2 · outbound

This paper cites What can we learn from the selective prediction and uncertainty estimation performance of 523 imagenet classifiers? InICLR, 2023.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation What can we learn from the selective prediction and uncertainty estimation performance of 523 imagenet classifiers? InICLR, 2023

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:19.347950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6507984f-46f0-4cb9-aafe-c113e62fcd7d · outbound

This paper cites Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:19.431099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7568562c-ffc8-489a-be3b-2de0f6cf89a2 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:19.585626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81a30f28-91e1-4efd-8a3c-1018db7a7458 · outbound

This paper cites Hierarchical Selective Classification.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Hierarchical Selective Classification

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:19.782803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af7c2ef5-176c-4ee1-80cf-57cf1e7f3097 · outbound

This paper cites Can Language Models Be Specific? How?.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Can Language Models Be Specific? How?

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:19.935671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 058bfcd8-b6d4-4665-a0fa-f94da2da1d9f · outbound

This paper cites A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions.ACM Trans.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions.ACM Trans

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:20.096207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71ebe582-46e2-4bd6-ad07-253dc46b77ba · outbound

This paper cites Optimized batch prompt- ing for cost-effective llms.Proceedings of the VLDB Endowment, 18(7):2172–2184, 2025.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Optimized batch prompt- ing for cost-effective llms.Proceedings of the VLDB Endowment, 18(7):2172–2184, 2025

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:20.245277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ff85f9b-29cd-4203-a847-9deb057d91b1 · outbound

This paper cites Survey of hallucination in natural language generation.ACM Comput.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Survey of hallucination in natural language generation.ACM Comput

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:20.390943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10c3a1af-80d0-4f53-95be-8462e8004b44 · outbound

This paper cites Weld, and Luke Zettlemoyer.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Weld, and Luke Zettlemoyer

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:20.523735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de57daed-0a24-4122-b6d4-6eab5d97592d · outbound

This paper cites Language Models (Mostly) Know What They Know.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Language Models (Mostly) Know What They Know

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:20.693204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 963c0683-82b9-41bb-8db6-69f75a324651 · outbound

This paper cites LLMs cannot (yet) match the specificity and simplicity of online commu- nities in long form question answering.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation LLMs cannot (yet) match the specificity and simplicity of online commu- nities in long form question answering

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:20.820609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63e738c7-908a-417f-a421-d3c84f0c127f · outbound

This paper cites Why Language Models Hallucinate.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Why Language Models Hallucinate

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:21.277478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c841976-6e62-4183-8c36-3727cf32f7de · outbound

This paper cites Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language gen- eration.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language gen- eration

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:21.679332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a8263f8-a378-45b9-bfea-591b6775a3e8 · outbound

This paper cites Generating with confidence: Uncertainty quantifi- cation for black-box large language models.Trans.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Generating with confidence: Uncertainty quantifi- cation for black-box large language models.Trans

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:21.911034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 525a0744-2b4f-47b7-8a32-59fe72544d64 · outbound

This paper cites Semnani, Harold Tried- man, Jialiang Xu, Isaac Dan Zhao, and Monica S.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Semnani, Harold Tried- man, Jialiang Xu, Isaac Dan Zhao, and Monica S

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:22.031035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7aabc83-b375-45d3-9a29-657f56ad7393 · outbound

This paper cites Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:22.328378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 383cf905-c7e6-4515-92b3-77810f688f36 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:21.796514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3b29ae8-3491-4756-a2b7-53b9c5577c63 · outbound

This paper cites Passonneau.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Passonneau

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:22.620005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc693f82-2110-42ae-a8da-6e08d7982855 · outbound

This paper cites gpt-oss-120b & gpt-oss-20b model card,.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation gpt-oss-120b & gpt-oss-20b model card,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:22.911980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0c1ac87-5f48-4af8-ae09-c00a38668115 · outbound

This paper cites findings-emnlp.938.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation findings-emnlp.938

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:22.182787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aae9824f-30ac-4f53-a5b2-264da2453a68 · outbound

This paper cites Qwen3 Technical Report.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Qwen3 Technical Report

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:23.294886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfd82b15-2ca8-41b1-b765-f5b78443a991 · outbound

This paper cites Factscore: Fine-grained atomic evaluation of fac- tual precision in long form text generation.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Factscore: Fine-grained atomic evaluation of fac- tual precision in long form text generation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:22.474547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc696b07-ad95-4b12-81b3-c596166fe372 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:23.553211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76dc8ab5-a7a2-4677-95d1-f8a7c5686630 · outbound

This paper cites Using Information Content to Evaluate Semantic Similarity in a Taxonomy.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Using Information Content to Evaluate Semantic Similarity in a Taxonomy

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:23.665589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc2de745-974b-4910-ac54-55fd8bd9fbde · outbound

This paper cites Crowdsourcing lightweight pyramids for manual summary evalua- tion.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Crowdsourcing lightweight pyramids for manual summary evalua- tion

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:23.802656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30a88078-6e8e-4172-bdf6-b5a0051cf52a · outbound

This paper cites Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:23.943252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4c432c6-d43b-4782-817d-a94df6867edd · outbound

This paper cites Fact-checking complex claims with program-guided reasoning.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Fact-checking complex claims with program-guided reasoning

Reference 38

Resolution: malformed identifier; no resolver link, observed 2026-08-03T00:03:23.181804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4bb4807-356a-48ae-ac20-5ca3309e174e · outbound

This paper cites LaMDA: Language Models for Dialog Applications.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation LaMDA: Language Models for Dialog Applications

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:24.194076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c56ae05-286a-476f-a8e9-d9f8cde308a5 · outbound

This paper cites A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:24.512527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 844412e3-cb99-43ab-bd4d-689e986fcb6a · outbound

This paper cites Benchmarking uncertainty quantification methods 11 for large language models with lm-polygraph.Trans.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Benchmarking uncertainty quantification methods 11 for large language models with lm-polygraph.Trans

Reference 42

Resolution: malformed identifier; no resolver link, observed 2026-08-03T00:03:24.632412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dceb6651-06fb-4c06-84d8-20f2d4629987 · outbound

This paper cites Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-08-03T00:03:36.793586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 73d555d5-83ce-4477-bbeb-e5850f33e588 · outbound

This paper cites Conditional validity of inductive conformal predictors.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Conditional validity of inductive conformal predictors

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:24.871070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0172bb90-0bdb-440c-9cf0-72d816bb6c8d · outbound

This paper cites The Llama 3 Herd of Models.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation The Llama 3 Herd of Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:24.063266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 976b333c-5e08-4ef4-a864-e03f6d0d9211 · outbound

This paper cites Wikidata: a free collaborative knowledgebase.Commun.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Wikidata: a free collaborative knowledgebase.Commun

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:25.181608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0ddef58-6d14-4d98-aaf5-1ecc70757836 · outbound

This paper cites A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:24.365784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd551a3b-de19-4f68-84fa-5ab8168b07ef · outbound

This paper cites Wong, Emine Yilmaz, Shuming Shi, and Zhaopeng Tu.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Wong, Emine Yilmaz, Shuming Shi, and Zhaopeng Tu

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:25.457827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49cdaf19-d6bb-4791-a661-4b6a92fb683b · outbound

This paper cites Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:25.580309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07165edd-cb18-47d5-a678-f6453b0d343f · outbound

This paper cites LUQ: long-text uncertainty quan- tification for llms.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation LUQ: long-text uncertainty quan- tification for llms

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:25.725434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b10b1654-e102-4ea5-ac6c-7e7e756138bd · outbound

This paper cites Finding a bal- anced degree of automation for summary evaluation.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Finding a bal- anced degree of automation for summary evaluation

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:26.102745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10e7bc47-e3c6-4f0d-a163-d56442932173 · outbound

This paper cites Machine-learning applications of algo- rithmic randomness.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Machine-learning applications of algo- rithmic randomness

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:25.045885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d250bc6d-9511-468c-abb8-1702ce2d2c91 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:25.298087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 352d25cc-3164-4b03-9ea4-98cdaa44d424 · outbound

This paper cites emnlp-main.299.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation emnlp-main.299

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:25.987020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e52a40d-2c82-484b-bc08-fd103fcdf216 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:26.369273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88442010-719a-47bb-9fd5-6440ce539bc7 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:26.541433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95a010c4-bfdd-455f-b444-36ce1c72e859 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:26.701898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fac7c6f2-1514-4e89-af4b-5089e12ada6a · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:26.842236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e6c2cfc-3487-4ef8-b1dc-57b36945df70 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:26.977413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 453e2e5e-758e-46b8-aa40-1996bbc739e9 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:27.132929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f70d3435-8b13-47fb-8dac-b1dba3fc8b6e · outbound

This paper cites ## Example 2 Input Text:Albert Einstein was a German-born theoretical physicist who is best known for developing the theory of relativity.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation ## Example 2 Input Text:Albert Einstein was a German-born theoretical physicist who is best known for developing the theory of relativity

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:27.228727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c01e1cc7-a6f3-4fda-8c07-22cf824df1cc · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:27.407060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c88dcfd-6ee8-4a9f-8b79-efe12785cbc1 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:27.573954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaf7b5bd-82fb-461b-b9cc-861a1f4d1249 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:27.672298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32fdbda2-04f6-4e0b-abc9-b0a0bf5a81ec · outbound

This paper cites ## Example 3.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation ## Example 3

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:27.772231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfa1fe89-9cd7-4c86-875d-384fdea5db8c · outbound

This paper cites - The confidence score must be a number between 0 and 100.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation - The confidence score must be a number between 0 and 100

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:27.935678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4825bd59-8234-4153-bb61-dbc477cfb919 · outbound

This paper cites # Review and Guidance Think step by step.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation # Review and Guidance Think step by step

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:28.567602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9698749-f8ac-4f36-84d7-72091ccac249 · outbound

This paper cites Reasoning: (your reasoning here).

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Reasoning: (your reasoning here)

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:28.640760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83275b95-6afa-4c30-99ed-3d61aa3d366e · outbound

This paper cites Reasoning: (your reasoning here).

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Reasoning: (your reasoning here)

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:28.722005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63367b78-08b3-4e9a-9e1d-04a858bda220 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:28.801719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 912f5daa-6c6f-4117-a3fb-c170ce1c97b7 · outbound

This paper cites Do not change the ENTITY.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Do not change the ENTITY

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:28.853542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78ce6ac8-cf0a-4402-90f8-66a2b91278d5 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:28.967140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8afe0436-0af3-46a2-844c-6aa991178476 · outbound

This paper cites Make the smallest logical generalization at each step.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Make the smallest logical generalization at each step

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:29.106743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d2fb7f8-9385-429b-88ef-33cad12ec796 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:29.222100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80231d5c-c67c-487a-ba32-7e669ca74ea6 · outbound

This paper cites The rest of the sentence must remain unchanged.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation The rest of the sentence must remain unchanged

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:29.336506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50092f4a-8f7e-4095-be27-dc6b73957c9e · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:29.394540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 987b8928-c385-457c-8514-b234aa8c98da · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:29.472539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0de129a9-9132-4615-b681-57c1a218160f · outbound

This paper cites In that case, output ‘STOP‘ and explain why.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation In that case, output ‘STOP‘ and explain why

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:29.553628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fab03f10-d41f-4c6e-903b-1e3625ae4947 · outbound

This paper cites Reasoning: I’m less confident about the exact city than the country.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Reasoning: I’m less confident about the exact city than the country

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:29.638115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8180c1e4-acad-478c-b257-cdc8caa39f5c · outbound

This paper cites Reasoning: Warsaw is a city in Poland, so this is a valid generalization.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Reasoning: Warsaw is a city in Poland, so this is a valid generalization

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:29.721562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e43fc28-cc15-4512-9861-a055f128a87e · outbound

This paper cites Reasoning: Poland is a European country.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Reasoning: Poland is a European country

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:29.801905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 810e7641-ef37-4d3c-846e-0fd906818f0c · outbound

This paper cites Reasoning: Further generalization would be too vague to retain meaning.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Reasoning: Further generalization would be too vague to retain meaning

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:29.879826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9142c29-37fb-4aa8-a4de-426a84f6fb9c · outbound

This paper cites - The confidence score must be a number between 0 and 100.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation - The confidence score must be a number between 0 and 100

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:29.979747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee3bfab6-b3cd-4760-8535-869fbfbfbec7 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:29.982761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dff476b-8cb3-425d-98cc-38f2377e7b7b · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:30.152180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf198785-bb7f-464a-8062-04318a961651 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:30.257769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f2cf9d0-3f8a-494d-ad3c-48b93479b4a6 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:30.366062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d19498ac-988b-43eb-be48-0ad17b4a6b3c · outbound

This paper cites # Review and Guidance Think step by step.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation # Review and Guidance Think step by step

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:30.516460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca3cf3f9-d889-4b35-97d2-35892a0b41b0 · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:30.676983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0df5b095-4413-4b42-9a61-32646701f89b · outbound

This paper cites an unresolved cited work.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Unresolved cited work

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:30.792610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c966921-fe4a-485b-9146-774c2024c823 · outbound

This paper cites SUPPORTED.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation SUPPORTED

Reference 102

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:30.889393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56b7d67e-7548-45b1-a4cd-1dd4ead418d0 · outbound

This paper cites • This is always the subject of the sentence.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation • This is always the subject of the sentence

Reference 103

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:31.009654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ed6573-2390-477c-92c0-2a2754b3d505 · outbound

This paper cites people” • For places, use terms like “cities.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation people” • For places, use terms like “cities

Reference 104

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:31.141006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10e72bea-d794-48b3-9597-0247f2833d82 · outbound

This paper cites • Use the format: How many [pluralized broad category] are there?.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation • Use the format: How many [pluralized broad category] are there?

Reference 105

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:31.233529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f682ba9-e3d5-4603-9a50-b782f5419e1d · outbound

This paper cites • Keep the rest of the sentence as intact as possible.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation • Keep the rest of the sentence as intact as possible

Reference 106

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:31.369420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee659bea-5a9c-4501-a56c-6d24c9cac79a · outbound

This paper cites French artists.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation French artists

Reference 107

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:31.485772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0165a781-cc4d-4732-89f5-9914deab2af1 · outbound

This paper cites These include sequence-level aggregates such as log-likelihood and (inverse) perplexity, as well as more local measures such as the minimum token log-probability.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation These include sequence-level aggregates such as log-likelihood and (inverse) perplexity, as well as more local measures such as the minimum token log-probability

Reference 108

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:31.595536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a5dfc84-a44e-416b-8e47-0ffffcd4be52 · outbound

This paper cites atoms” evaluates ranking over the original atom set, whereas “all.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation atoms” evaluates ranking over the original atom set, whereas “all

Reference 109

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:31.683006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f4a6fee-6b97-4666-bfbd-32d34f359cb8 · outbound

This paper cites findings-emnlp.111/.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation findings-emnlp.111/

Reference 111

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:21.119154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89f11618-63f6-4afb-82ba-cd14311009be · outbound

This paper cites URL https://aclanthology.org/ N04-1019/.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation URL https://aclanthology.org/ N04-1019/

Reference 152

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:22.774498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba56e52f-5f0e-47e8-824c-41ae244c2063 · outbound

This paper cites Ice Bucket Challenge.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Ice Bucket Challenge

Reference 531

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:26.231798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f4e32de-3428-4912-bf75-d692f744d3d8 · outbound

This paper cites doi: 10.18653/v1/2024.findings-emnlp.

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation doi: 10.18653/v1/2024.findings-emnlp

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T00:03:20.942117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4b431fc0-3dcf-47d9-93e3-d84b90fc62ca · inbound

Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems cites this paper.

Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-03T02:05:13.522389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d3826a06-f7a8-4ad7-8f30-30abd89d9f14 · inbound

Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems cites this paper.

Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-03T02:05:13.522389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.