mlsanityData to 7 Oct 2026

Faithful Reasoning Using Large Language Models

arXiv 2208.14271 ↗First posted 30 Aug 2022cs.AI cs.CLcited by 130

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Although contemporary large language models (LMs) demonstrate impressive question-answering capabilities, their answers are typically the product of a single call to the model. This entails an unwelcome degree of opacity and compromises performance, especially on problems that are inherently multi-step. To address these limitations, we show how LMs can be made to perform faithful multi-step reasoning via a process whose causal structure mirrors the underlying logical structure of the problem. Our approach works by chaining together reasoning steps, where each step results from calls to two fine-tuned LMs, one for selection and one for inference, to produce a valid reasoning trace. Our method carries out a beam search through the space of reasoning traces to improve reasoning quality. We demonstrate the effectiveness of our model on multi-step logical deduction and scientific question-answering, showing that it outperforms baselines on final answer accuracy, and generates humanly interpretable reasoning traces whose validity can be checked by the user.

Key facts. Cited by 130 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 28 of its 36 references that are in the map. First posted on arXiv 30 Aug 2022.

Builds on

28 of 36 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Language models show human-like content effects on reasoning tasks14 Jul
  2. 2022On the Paradox of Learning to Reason from Data23 May
  3. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning19 May
  4. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Models30 Nov

Other references · 24

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  4. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  6. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  7. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  8. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  9. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  10. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  11. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  12. 2021Ethical and social risks of harm from Language Modelscited by 957
12 more
  1. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  2. 2013Generating Sequences With Recurrent Neural Networkscited by 549
  3. 2016Adaptive Computation Time for Recurrent Neural Networkscited by 479
  4. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 309
  5. 2021PonderNet: Learning to Pondercited by 156
  6. 2021Explaining Answers with Entailment Treescited by 148
  7. 2020NILE : Natural Language Inference with Faithful Natural Language Explanationscited by 96
  8. 2020PRover: Proof Generation for Interpretable Reasoning over Rulescited by 53
  9. 2020Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answeringcited by 49
  10. 2022Natural Language Deduction through Search over Statement Compositionscited by 35
  11. 2020Critical Thinking for Language Modelscited by 31
  12. 2022Entailment Tree Explanations via Iterative Retrieval-Generation Reasonercited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 23; 2023: 36; 2024: 33; 2025: 23; 2026: 15.

130 papers.

Sort:

By area:

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  3. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  4. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 668
  5. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  6. 2023Faith and Fate: Limits of Transformers on Compositionalitycited by 496
  7. 2023Augmented Language Models: a Surveycited by 398
  8. 2023Language Models can Solve Computer Taskscited by 371
  9. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 338
  10. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 334
  11. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  12. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
38 more
  1. 2022Reasoning with Language Model Prompting: A Surveycited by 251
  2. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  3. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 230
  4. 2023What Algorithms can Transformers Learn? A Study in Length Generalizationcited by 198
  5. 2022Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionalscited by 191
  6. 2022Talking About Large Language Modelscited by 174
  7. 2025Reasoning Models Know When They're Right: Probing Hidden States for Self-Verificationcited by 154
  8. 2023Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulnesscited by 130
  9. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
  10. 2023Deductive Verification of Chain-of-Thought Reasoningcited by 122
  11. 2022Teaching Algorithmic Reasoning via In-context Learningcited by 111
  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. 2023Learning From Mistakes Makes LLM Better Reasonercited by 97
  15. 2023Cumulative Reasoning with Large Language Modelscited by 94
  16. 2022ChatGPT: The End of Online Exam Integrity?cited by 88
  17. 2023Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanationscited by 85
  18. 2023ReCEval: Evaluating Reasoning Chains via Correctness and Informativenesscited by 76
  19. 2024RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generationcited by 75
  20. 2024LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Modelscited by 70
  21. 2022LAMBADA: Backward Chaining for Automated Reasoning in Natural Languagecited by 66
  22. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  23. 2023Natural Language Reasoning, A Surveycited by 61
  24. 2023AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applicationscited by 53
  25. 2024LLaRA: Supercharging Robot Learning Data for Vision-Language Policycited by 51
  26. 2023Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiencycited by 46
  27. 2022Two-stage LLM Fine-tuning with Less Specialization and More Generalizationcited by 39
  28. 2024Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thoughtcited by 37
  29. 2025Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoningcited by 36
  30. 2023Affective Faces for Goal-Driven Dyadic Communicationcited by 34
  31. 2023Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models through Logiccited by 34
  32. 2022Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Modelcited by 32
  33. 2024Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphscited by 32
  34. 2023FactCHD: Benchmarking Fact-Conflicting Hallucination Detectioncited by 29
  35. 2024The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Modelscited by 29
  36. 2024TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysiscited by 28
  37. 2024How Interpretable are Reasoning Explanations from Prompting Large Language Models?cited by 27
  38. 2023Interpretable Unified Language Checkingcited by 26

50 most cited of 130 All 130 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Question Decomposition Improves the Faithfulness of Model-Generated Reasoning
  2. 2025Follow the Path: Reasoning over Knowledge Graph Paths to Improve Large Language Model Factuality
  3. 2024Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning
  4. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  5. 2024LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models
  6. 2024FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering
  7. 2025Thinking in Many Modes: How Composite Reasoning Elevates Large Language Model Performance with Limited Data
  8. 2024Refining Answer Distributions for Improved Large Language Model Reasoning