mlsanityData to 7 Oct 2026

Measuring Faithfulness in Chain-of-Thought Reasoning

arXiv 2307.13702 ↗First posted 17 Jul 2023cs.AI cs.CL cs.LGcited by 668

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

Large language models (LLMs) perform better when they produce step-by-step, "Chain-of-Thought" (CoT) reasoning before answering a question, but it is unclear if the stated reasoning is a faithful explanation of the model's actual reasoning (i.e., its process for answering the question). We investigate hypotheses for how CoT reasoning may be unfaithful, by examining how the model predictions change when we intervene on the CoT (e.g., by adding mistakes or paraphrasing it). Models show large variation across tasks in how strongly they condition on the CoT when predicting their answer, sometimes relying heavily on the CoT and other times primarily ignoring it. CoT's performance boost does not seem to come from CoT's added test-time compute alone or from information encoded via the particular phrasing of the CoT. As models become larger and more capable, they produce less faithful reasoning on most tasks we study. Overall, our results suggest that CoT can be faithful if the circumstances such as the model size and task are carefully chosen.

Key facts. Cited by 668 papers in the map (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 34 of its 47 references that are in the map. First posted on arXiv 17 Jul 2023.

Builds on

34 of 47 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting7 May
  2. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models6 May
  3. 2023Faithful Chain-of-Thought Reasoning31 Jan
  4. 2022Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango16 Sep
  5. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Models21 May
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  5. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  6. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  7. 2017Deep reinforcement learning from human preferencescited by 3,846
  8. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  9. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  10. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  11. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  12. 2020Learning to summarize from human feedbackcited by 2,562
16 more
  1. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  2. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  3. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  4. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  5. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  6. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  7. 2020Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learningcited by 216
  8. 2022Measuring Progress on Scalable Oversight for Large Language Modelscited by 212
  9. 2023Inverse Scaling: When Bigger Isn't Bettercited by 205
  10. 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 171
  11. 2022Language Models as Agent Modelscited by 131
  12. 2022Faithful Reasoning Using Large Language Modelscited by 130
  13. 2017What do we need to build explainable AI systems for the medical domain?cited by 127
  14. 2022Explanations from Large Language Models Make Small Reasoners Bettercited by 123
  15. 2022Rationale-Augmented Ensembles in Language Modelscited by 111
  16. 2022Successive Prompting for Decomposing Complex Questionscited by 94

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 26; 2024: 96; 2025: 166; 2026: 380.

668 papers.

Sort:

By area:

  1. 2024OpenAI o1 System Cardcited by 1,220
  2. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  3. 2023XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Modelscited by 477
  4. 2024LLaVA-CoT: Let Vision Language Models Reason Step-by-Stepcited by 446
  5. 2025Reasoning Models Don't Always Say What They Thinkcited by 388
  6. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 338
  7. 2023Explainability for Large Language Models: A Surveycited by 331
  8. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agentscited by 319
  9. 2024Alignment faking in large language modelscited by 316
  10. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 308
  11. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningcited by 257
  12. 2023Think before you speak: Training Language Models With Pause Tokenscited by 254
38 more
  1. 2024Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMscited by 246
  2. 2024Compressed Chain of Thought: Efficient Reasoning Through Dense Representationscited by 192
  3. 2024Let's Think Dot by Dot: Hidden Computation in Transformer Language Modelscited by 186
  4. 2023AI Deception: A Survey of Examples, Risks, and Potential Solutionscited by 185
  5. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  6. 2025Chain-of-Thought Reasoning In The Wild Is Not Always Faithfulcited by 166
  7. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 140
  8. 2023Large Language Models can Strategically Deceive their Users when Put Under Pressurecited by 132
  9. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyondcited by 131
  10. 2025Thought Anchors: Which LLM Reasoning Steps Matter?cited by 126
  11. 2024Tokenization counts: the impact of tokenization on arithmetic in frontier LLMscited by 112
  12. 2025Natural Emergent Misalignment from Reward Hacking in Production RLcited by 111
  13. 2024Rethinking Interpretability in the Era of Large Language Modelscited by 110
  14. 2024Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoningcited by 108
  15. 2025Agentic Large Language Models, a surveycited by 105
  16. 2024Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Modelscited by 104
  17. 2024SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationalescited by 102
  18. 2024Are self-explanations from Large Language Models faithful?cited by 101
  19. 2023Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Modelscited by 92
  20. 2024A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendationscited by 84
  21. 2024A Primer on the Inner Workings of Transformer-based Language Modelscited by 83
  22. 2023How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questionscited by 82
  23. 2025When Chain of Thought is Necessary, Language Models Struggle to Evade Monitorscited by 81
  24. 2024Formal Mathematical Reasoning: A New Frontier in AIcited by 80
  25. 2024A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasonerscited by 73
  26. 2023On Measuring Faithfulness or Self-consistency of Natural Language Explanationscited by 71
  27. 2023Using Large Language Models for Hyperparameter Optimizationcited by 71
  28. 2023Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaborationcited by 70
  29. 2024OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AIcited by 70
  30. 2024In-context Learning with Retrieved Demonstrations for Language Models: A Surveycited by 69
  31. 2025V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoningcited by 66
  32. 2025Effectively Controlling Reasoning Models through Thinking Interventioncited by 63
  33. 2023Preventing Language Models From Hiding Their Reasoningcited by 62
  34. 2025Evaluating Step-by-step Reasoning Traces: A Surveycited by 62
  35. 2024Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMscited by 52
  36. 2025When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMscited by 51
  37. 2024Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizingcited by 49
  38. 2025CoT Red-Handed: Stress Testing Chain-of-Thought Monitoringcited by 49

50 most cited of 668 All 668 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability
  2. 2024LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step Arithmetics
  3. 2025A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages
  4. 2026Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations
  5. 2026Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of-Thought Under Knowledge Conflict
  6. 2026Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability?
  7. 2024Understanding Chain-of-Thought in LLMs through Information Theory
  8. 2025Long Chain-of-Thought Reasoning Across Languages