Paper Citation Record · LEDGER

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes

As of 20 August 2026, this Paper Citation Record lists 85 of 85 outbound references and 2 inbound Pith citation observations for arXiv:2507.22940.

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

pith.paper-citation-record.v1
2507.22940 v2

Coverage vector

measured 85 of 85 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:03:15.426142Z

measured 87 of 87 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T12:08:10.552789Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

85 of 85 outbound references displayed

verified exact2
verified fuzzy25
unresolved56
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

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

Outbound references

Observation a15e3588-c29a-4b9e-a209-80d92dd4745d · outbound

This paper cites Language models are few-shot learners,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Language models are few-shot learners,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.034973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a703d20e-27af-49b3-890e-7be3277f1b41 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Constitutional AI: Harmlessness from AI Feedback

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.039775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddd8c491-abf3-4d90-8371-5138374303c5 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes LLaMA: Open and Efficient Foundation Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.045001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1281603e-5df3-4ead-8fad-1d3b24c5bf5b · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Gemini: A Family of Highly Capable Multimodal Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.049765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bcb41a8-d4a3-4cd1-b4bd-d24ef379f2bf · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.054477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c7dee8c-23be-4991-b986-28beaf76540e · outbound

This paper cites Qwen Technical Report.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Qwen Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.059198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 670d17e9-ea99-4c80-8b44-5ffbab56cb8b · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.064263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45787ff0-20a7-45c5-99a3-97e623309e16 · outbound

This paper cites Qwq-32b: Embracing the power of reinforcement learning,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Qwq-32b: Embracing the power of reinforcement learning,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.073137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35d7ce23-942b-49c5-ae84-0aff7cbff47b · outbound

This paper cites Learning to reason with llms,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Learning to reason with llms,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.077594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c8e32c1-5a10-46cd-ab4f-db81477f63e4 · outbound

This paper cites Claude 3.7 sonnet and claude code,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Claude 3.7 sonnet and claude code,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.082334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3ddf8ae-848d-484b-a1e6-3c2555323dd2 · outbound

This paper cites Large Language Models for Disease Diagnosis: A Scoping Review.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Large Language Models for Disease Diagnosis: A Scoping Review

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.086673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 325289f8-ae28-4f7c-bacf-36aeac9ad512 · outbound

This paper cites Evaluating LLM -- Generated Multimodal Diagnosis from Medical Images and Symptom Analysis.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Evaluating LLM -- Generated Multimodal Diagnosis from Medical Images and Symptom Analysis

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.091368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2df7d58-7eb6-465e-a51a-7b607ffab679 · outbound

This paper cites Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.095819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5504c403-47e9-4d4a-a0ca-2b3860540945 · outbound

This paper cites Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.100738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d189ea0-b83d-4ba7-8d00-7ece3006bd71 · outbound

This paper cites INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.105798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7006b9f1-b8a9-4c53-83a3-6dd0ff2fdb86 · outbound

This paper cites Finqapt: Empowering financial decisions with end-to-end llm-driven question answering pipeline,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Finqapt: Empowering financial decisions with end-to-end llm-driven question answering pipeline,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.110881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c604c2ed-a02e-4b43-9574-7c5cdbdb4d51 · outbound

This paper cites Order Matters in Hallucination: Reasoning Order as Benchmark and Reflexive Prompting for Large-Language-Models.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Order Matters in Hallucination: Reasoning Order as Benchmark and Reflexive Prompting for Large-Language-Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.115336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2deed91-ab7e-489b-93ba-505d2a67a9f3 · outbound

This paper cites CMMLU: measuring massive multitask language understanding in chinese,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes CMMLU: measuring massive multitask language understanding in chinese,

Reference 18

Resolution: malformed identifier; no resolver link, observed 2026-08-15T18:03:15.120245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 737419bd-99e6-401f-956e-3993d1de2778 · outbound

This paper cites Truthfulqa: Measuring how models mimic human falsehoods,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Truthfulqa: Measuring how models mimic human falsehoods,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.124874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eba5314c-e4e5-4c89-be09-c2bc3b52ce52 · outbound

This paper cites C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.772475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ac486191-a068-4dfb-a98a-4e058a533abd · outbound

This paper cites Factuality enhanced language models for open-ended text generation,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Factuality enhanced language models for open-ended text generation,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.758204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0faf971c-8388-4047-b042-60b13998e140 · outbound

This paper cites SKILL: structured knowledge infusion for large language models,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes SKILL: structured knowledge infusion for large language models,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.138673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cb5748c-c181-4272-9707-55de5f7821af · outbound

This paper cites Contrastive learning reduces hallucination in conversations,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Contrastive learning reduces hallucination in conversations,

Reference 23

Resolution: verified exact; doi, observed 2026-08-15T18:03:16.742961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8b54acc6-1798-464c-91bf-c21693d8f3b5 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.148064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1461a0bd-247b-476f-81a4-fffb29c0e41e · outbound

This paper cites Mechanistic Interpretability for AI Safety -- A Review.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Mechanistic Interpretability for AI Safety -- A Review

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.157880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e875050-bdb9-4f1b-9283-55b503193cb2 · outbound

This paper cites On the dangers of stochastic parrots: Can language models be too big?.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes On the dangers of stochastic parrots: Can language models be too big?

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.727790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e2439061-1e03-432d-9905-3a696d96c87d · outbound

This paper cites Sparks of Artificial General Intelligence: Early experiments with GPT-4.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Sparks of Artificial General Intelligence: Early experiments with GPT-4

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.171506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26aa5c46-90c4-41e5-86b4-be766c1a27e7 · outbound

This paper cites GPT-4 Technical Report.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes GPT-4 Technical Report

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.176522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b589ed74-e21d-4091-87d5-2473db998aca · outbound

This paper cites Microsoft Bing: Get to know Bing,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Microsoft Bing: Get to know Bing,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.712392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f5384afd-c889-400f-ba3c-8c6333b7c8d6 · outbound

This paper cites [Online].

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes [Online]

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.680863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 14189d15-bb15-4b9c-b4af-dba1b88fafe2 · outbound

This paper cites an unresolved cited work.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:03:16.665886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ca075c6c-b6f4-482d-962e-e4e02412d3e5 · outbound

This paper cites an unresolved cited work.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:03:16.651350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0386fc58-86dd-4e69-82b9-c1bd0fa82b1b · outbound

This paper cites Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.208124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b27f6346-904f-4d31-b57d-483dcd3c058b · outbound

This paper cites Available: https://www.microsoft.com/en-us/bing.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Available: https://www.microsoft.com/en-us/bing

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.696479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 76e5f2bb-69a3-4141-9ef1-914304b0c6d1 · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Learn to explain: Multimodal reasoning via thought chains for science question answering,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.621437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 715d0362-a11b-491c-8cd7-4fe1e6eafcbe · outbound

This paper cites WebGPT: Browser-assisted question-answering with human feedback.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes WebGPT: Browser-assisted question-answering with human feedback

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.225818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 559b081b-0c80-4b74-915f-6345a752d75e · outbound

This paper cites Webcpm: Interactive web search for chinese long- form question answering,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Webcpm: Interactive web search for chinese long- form question answering,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.230528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7329238-d0d6-44c3-a748-366e42d93b7c · outbound

This paper cites The reversal curse: Llms trained on.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes The reversal curse: Llms trained on

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.596007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0bda6a5d-60e8-4ce0-b4f4-756fa9a48ec9 · outbound

This paper cites Survey of hallucination in natural language generation,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Survey of hallucination in natural language generation,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.636748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 928116c9-de0f-43ce-8e46-b357386115d7 · outbound

This paper cites Available: https://doi.org/10.1145/3571730.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Available: https://doi.org/10.1145/3571730

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.217039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8b1339a-ba1c-40ef-b4db-252f153fd464 · outbound

This paper cites MISGENDERED: limits of large language models in understanding pronouns,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes MISGENDERED: limits of large language models in understanding pronouns,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.252829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ce2cc9b-185e-490f-a00a-e11137e6246f · outbound

This paper cites Knowledge neurons in pretrained transformers,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Knowledge neurons in pretrained transformers,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.257431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46cf68bc-395a-4ef4-bde2-cfcc16163b02 · outbound

This paper cites Locating and editing factual associations in GPT,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Locating and editing factual associations in GPT,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.566089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7a1cf624-05dc-4f02-a156-d9f08fc58eff · outbound

This paper cites Improving factuality and reasoning in language models through multiagent debate,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Improving factuality and reasoning in language models through multiagent debate,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.550476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b1192ac6-21eb-4fed-8d84-d5ada10471d4 · outbound

This paper cites Understanding catastrophic forgetting in language models via implicit inference,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Understanding catastrophic forgetting in language models via implicit inference,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.581022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8a8a640f-38fc-4591-935f-35ff28a86700 · outbound

This paper cites Bias and Fairness in Large Language Models: A Survey.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Bias and Fairness in Large Language Models: A Survey

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.244043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e2dfbe5-f929-45c6-ad0a-786c7a9b4a94 · outbound

This paper cites Bias and Fairness in Large Language Models: A Survey.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Bias and Fairness in Large Language Models: A Survey

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.248522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13d67ff1-81f3-40fe-a878-a78b5149c074 · outbound

This paper cites Dola: Decoding by contrasting layers improves factuality in large language models,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Dola: Decoding by contrasting layers improves factuality in large language models,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.505457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2f2eede1-b76a-497b-a974-34a5e89c215a · outbound

This paper cites Improving language models by retrieving from trillions of tokens,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Improving language models by retrieving from trillions of tokens,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.490560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 04a1613a-439a-4e90-9fd8-ad2f8450207e · outbound

This paper cites Internet-augmented language models through few-shot prompting for open-domain question answering.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Internet-augmented language models through few-shot prompting for open-domain question answering

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.292797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 184e045a-675c-4fa9-a5fd-cd3289174221 · outbound

This paper cites Rethinking with Retrieval: Faithful Large Language Model Inference.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Rethinking with Retrieval: Faithful Large Language Model Inference

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.302072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 456833a8-8fea-4aa8-b915-ef5809a1e2eb · outbound

This paper cites LM vs LM: detecting factual errors via cross examination,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes LM vs LM: detecting factual errors via cross examination,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.270542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0c610ac-83b6-4e09-8fff-61838567a76e · outbound

This paper cites Generate rather than retrieve: Large language models are strong context generators,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Generate rather than retrieve: Large language models are strong context generators,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.534423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7c03668b-0cf7-4ec4-bef5-cbec39ad4d73 · outbound

This paper cites ”according to.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes ”according to

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.520011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0053207f-b76d-465c-9c10-021ffe283d98 · outbound

This paper cites SAIL: Search-Augmented Instruction Learning.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes SAIL: Search-Augmented Instruction Learning

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.320474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afc209e6-ea1d-447c-ba99-250469990d92 · outbound

This paper cites Decoupled context processing for context augmented language modeling,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Decoupled context processing for context augmented language modeling,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.449676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 54223f28-3cf7-4c84-8fc9-35be5a160c0a · outbound

This paper cites G-MAP: general memory-augmented pre-trained language model for domain tasks,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes G-MAP: general memory-augmented pre-trained language model for domain tasks,

Reference 57

Resolution: verified exact; doi, observed 2026-08-15T18:03:15.633949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1f20ef7d-40a0-4bec-ba68-9acc7787aa29 · outbound

This paper cites The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.334546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a37df6f-29b3-4ca4-97cf-413fb9b8c2f9 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Chain-of-thought prompting elicits reasoning in large language models,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.339758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c0bb3d0-5fd7-40b9-bd31-9a0f4c362cbc · outbound

This paper cites Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions,

Reference 60

Resolution: malformed identifier; no resolver link, observed 2026-08-15T18:03:15.306845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d086de5-e5b8-4a23-9386-6c76f13245af · outbound

This paper cites Atlas: Few-shot learning with retrieval augmented language models,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Atlas: Few-shot learning with retrieval augmented language models,

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.475090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5d7cab6a-d398-45cb-9c58-1d26511bb7f7 · outbound

This paper cites REPLUG: retrieval-augmented black- box language models,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes REPLUG: retrieval-augmented black- box language models,

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.316124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cfadc84-5c2e-4228-8832-5abc2a0321fc · outbound

This paper cites LoRA Learns Less and Forgets Less.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes LoRA Learns Less and Forgets Less

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.357576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2239fb46-80d1-49ce-8f4b-9211b30804ca · outbound

This paper cites Decoupled weight decay regularization,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Decoupled weight decay regularization,

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.391642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation de75e81d-39e3-4939-8d72-b9703538d3ad · outbound

This paper cites Proximal Policy Optimization Algorithms.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Proximal Policy Optimization Algorithms

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.366675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9af4a418-ec9d-42f7-a66f-ddc5ba04a6a4 · outbound

This paper cites A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.371184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 291a3523-2418-4374-8a24-16168096b4c8 · outbound

This paper cites A Survey on LLM-as-a-Judge.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes A Survey on LLM-as-a-Judge

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.380576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acc37e6c-6a6b-48ff-a366-79824e0a04c8 · outbound

This paper cites FLAIR: An easy-to-use framework for state-of-the- art NLP,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes FLAIR: An easy-to-use framework for state-of-the- art NLP,

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.424176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 450acbdb-be2d-4714-90ca-a5bfaec99d70 · outbound

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

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Instruction tuning for large language models: A survey,

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.348513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03fd2163-99c4-4688-8658-abbb84329f4b · outbound

This paper cites Lora: Low-rank adaptation of large language models,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Lora: Low-rank adaptation of large language models,

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.408784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a8ee7b24-83d0-4bd9-b38f-c879b987989a · outbound

This paper cites Lighteval: A lightweight framework for llm evaluation,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Lighteval: A lightweight framework for llm evaluation,

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.345793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f3f3a85f-81f4-485b-b111-13ea0cf93655 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Efficient memory management for large language model serving with pagedattention,

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.330377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ef580638-c827-423f-b193-3e9c54128cf6 · outbound

This paper cites DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.417052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f684f81b-bfc8-496d-87b7-22b60993e257 · outbound

This paper cites A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.376088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24df5dcb-a85c-4355-81b9-2ec94314926a · outbound

This paper cites Open r1: A fully open reproduction of deepseek-r1,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Open r1: A fully open reproduction of deepseek-r1,

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.376272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 80afaed0-6d58-4f34-8660-bd58f1d3a721 · outbound

This paper cites Gemini 2.0 flash,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Gemini 2.0 flash,

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:03:16.361249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 36c1c478-8bdb-49fd-8a1c-a4f9eae35fdd · outbound

This paper cites LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.393616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c331b2c8-9376-400f-81ec-44c44298a02d · outbound

This paper cites DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.421740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2ee8123-3fea-457a-9d42-8e0d9ecfbdd8 · outbound

This paper cites An analysis of encoder representations in transformer-based machine translation,.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes An analysis of encoder representations in transformer-based machine translation,

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.426142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3c5881c-adba-43e6-ae71-bf288a10697e · outbound

This paper cites Available: https://doi.org/10.1145/3442188.3445922.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Available: https://doi.org/10.1145/3442188.3445922

Reference 623

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.167069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9227a4b4-1a4b-4cc3-8a05-906517eae6a1 · outbound

This paper cites HuggingFace's Transformers: State-of-the-art Natural Language Processing.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes HuggingFace's Transformers: State-of-the-art Natural Language Processing

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.403479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 518519e3-ca66-492f-af2a-c65d80a00a9e · outbound

This paper cites Internet-augmented language models through few-shot prompting for open-domain question answering.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes Internet-augmented language models through few-shot prompting for open-domain question answering

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.297259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21e9eb86-ad22-4b40-aba5-dc4d67e50d0b · outbound

This paper cites GPT-4 Technical Report.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes GPT-4 Technical Report

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.181466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e7d88cc-daad-4bb5-8de9-6eaaeef674b6 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.152972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0924e61-864d-4718-93ad-d217650a8504 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T18:03:15.068746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 104cf56b-0a3d-410a-88c1-2ceda34d5c0b · inbound

Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution cites this paper.

Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-20T06:48:05.981542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 294bc273-77c1-43e4-b4c7-f686bdddfeab · inbound

Matter to Mechanism: A Benchmark for AI Co-Scientists in Materials and Battery Research cites this paper.

Matter to Mechanism: A Benchmark for AI Co-Scientists in Materials and Battery Research Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes

Reference 48

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T12:12:07.831497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.