mlsanityData to 7 Oct 2026

Faithful Chain-of-Thought Reasoning

arXiv 2301.13379 ↗First posted 31 Jan 2023cs.CLcited by 285

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

Abstract (arXiv)

While Chain-of-Thought (CoT) prompting boosts Language Models' (LM) performance on a gamut of complex reasoning tasks, the generated reasoning chain does not necessarily reflect how the model arrives at the answer (aka. faithfulness). We propose Faithful CoT, a reasoning framework involving two stages: Translation (Natural Language query rightarrow symbolic reasoning chain) and Problem Solving (reasoning chain rightarrow answer), using an LM and a deterministic solver respectively. This guarantees that the reasoning chain provides a faithful explanation of the final answer. Aside from interpretability, Faithful CoT also improves empirical performance: it outperforms standard CoT on 9 of 10 benchmarks from 4 diverse domains, with a relative accuracy gain of 6.3% on Math Word Problems (MWP), 3.4% on Planning, 5.5% on Multi-hop Question Answering (QA), and 21.4% on Relational Inference. Furthermore, with GPT-4 and Codex, it sets the new state-of-the-art few-shot performance on 7 datasets (with 95.0+ accuracy on 6 of them), showing a strong synergy between faithfulness and accuracy.

Key facts. Cited by 285 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 28 of its 42 references that are in the map. First posted on arXiv 31 Jan 2023.

Builds on

28 of 42 references.

Closest ancestors · 6

Same direction, newest first

  1. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks22 Nov
  2. 2022Large Language Models are Zero-Shot Reasoners24 May
  3. 2022Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations24 May
  4. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Models21 May
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 22

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  6. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  7. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,359
  8. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  9. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  10. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  11. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  12. 2022PAL: Program-aided Language Modelscited by 635
10 more
  1. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  2. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  3. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
  4. 2016Solving General Arithmetic Word Problemscited by 353
  5. 2021A Diverse Corpus for Evaluating and Developing English Math Word Problem Solverscited by 314
  6. 2019CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Textcited by 155
  7. 2019Learning to Deceive with Attention-Based Explanationscited by 111
  8. 2022Interpreting Language Models with Contrastive Explanationscited by 91
  9. 2022Limitations of Language Models in Arithmetic and Symbolic Inductioncited by 71
  10. 2017The Promise and Peril of Human Evaluation for Model Interpretabilitycited by 52

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 65; 2024: 75; 2025: 75; 2026: 70.

285 papers.

Sort:

By area:

  1. 2023A Survey of Large Language Modelscited by 2,537
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  4. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  5. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 668
  6. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spacescited by 580
  7. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  8. 2025Reasoning Models Don't Always Say What They Thinkcited by 388
  9. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 379
  10. 2024Token-Budget-Aware LLM Reasoningcited by 242
  11. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 238
  12. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planningcited by 204
38 more
  1. 2023MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoningcited by 195
  2. 2025Chain-of-Thought Reasoning In The Wild Is Not Always Faithfulcited by 166
  3. 2023SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoningcited by 157
  4. 2023Deductive Verification of Chain-of-Thought Reasoningcited by 122
  5. 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thoughtcited by 118
  6. 2024Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoningcited by 108
  7. 2023Question Decomposition Improves the Faithfulness of Model-Generated Reasoningcited by 107
  8. 2025Agentic Large Language Models, a surveycited by 105
  9. 2024Large Language Models Meet NLP: A Surveycited by 102
  10. 2024SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationalescited by 102
  11. 2023SatLM: Satisfiability-Aided Language Models Using Declarative Promptingcited by 100
  12. 2024Chain of Thoughtlessness? An Analysis of CoT in Planningcited by 100
  13. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  14. 2023Cumulative Reasoning with Large Language Modelscited by 94
  15. 2023Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Modelscited by 92
  16. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 84
  17. 2024LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shiftscited by 80
  18. 2024Prover-Verifier Games improve legibility of LLM outputscited by 79
  19. 2023Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communicationcited by 78
  20. 2023Boosting Language Models Reasoning with Chain-of-Knowledge Promptingcited by 77
  21. 2024If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agentscited by 77
  22. 2023ReCEval: Evaluating Reasoning Chains via Correctness and Informativenesscited by 76
  23. 2024Calibrating Large Language Models with Sample Consistencycited by 72
  24. 2023On Measuring Faithfulness or Self-consistency of Natural Language Explanationscited by 71
  25. 2023Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarizationcited by 70
  26. 2023Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaborationcited by 70
  27. 2024LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Modelscited by 70
  28. 2025Are DeepSeek R1 And Other Reasoning Models More Faithful?cited by 69
  29. 2023Towards Better Chain-of-Thought Prompting Strategies: A Surveycited by 62
  30. 2024TrustAgent: Towards Safe and Trustworthy LLM-based Agentscited by 62
  31. 2023In-context Example Selection with Influencescited by 60
  32. 2023Grammar Prompting for Domain-Specific Language Generation with Large Language Modelscited by 58
  33. 2024OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Modelscited by 54
  34. 2025Empowering LLMs with Logical Reasoning: A Comprehensive Surveycited by 51
  35. 2023Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoningcited by 49
  36. 2024Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correctioncited by 45
  37. 2023SelfEvolve: A Code Evolution Framework via Large Language Modelscited by 43
  38. 2024On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Modelscited by 42

50 most cited of 285 All 285 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?
  2. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
  3. 2026Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning
  4. 2024Faithful Logical Reasoning via Symbolic Chain-of-Thought
  5. 2025Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
  6. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters
  7. 2024Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step
  8. 2024ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting