mlsanityData to 14 Oct 2026

Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations

arXiv 2205.11822 ↗First posted 24 May 2022cs.CLcited by 159

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

Abstract (arXiv)

Despite their impressive capabilities, large pre-trained language models (LMs) struggle with consistent reasoning; recently, prompting LMs to generate explanations that self-guide the inference has emerged as a promising direction to amend this. However, these approaches are fundamentally bounded by the correctness of explanations, which themselves are often noisy and inconsistent. In this work, we develop Maieutic Prompting, which infers a correct answer to a question even from the noisy and inconsistent generations of LM. Maieutic Prompting induces a tree of explanations abductively (e.g. X is true, because ...) and recursively, then frames the inference as a satisfiability problem over these explanations and their logical relations. We test Maieutic Prompting for true/false QA on three challenging benchmarks that require complex commonsense reasoning. Maieutic Prompting achieves up to 20% better accuracy than state-of-the-art prompting methods, and as a fully unsupervised approach, performs competitively with supervised models. We also show that Maieutic Prompting improves robustness in inference while providing interpretable rationales.

Key facts. Cited by 159 papers in the map (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 40 of its 54 references that are in the map. First posted on arXiv 24 May 2022.

Builds on

40 of 54 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 38

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  6. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  7. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  8. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  9. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  10. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  11. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 476
  12. 2020Towards a Human-like Open-Domain Chatbotcited by 470
26 more
  1. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  2. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  3. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 364
  4. 2019Abductive Commonsense Reasoningcited by 301
  5. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  6. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 263
  7. 2022Can language models learn from explanations in context?cited by 249
  8. 2019Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Flycited by 243
  9. 2018Techniques for Interpretable Machine Learningcited by 238
  10. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 214
  11. 2020Unsupervised Commonsense Question Answering with Self-Talkcited by 161
  12. 2020NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraintscited by 149
  13. 2020WT5?! Training Text-to-Text Models to Explain their Predictionscited by 148
  14. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 113
  15. 2022CommonsenseQA 2.0: Exposing the Limits of AI through Gamificationcited by 109
  16. 2021UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmarkcited by 98
  17. 2021CREAK: A Dataset for Commonsense Reasoning over Entity Knowledgecited by 88
  18. 2021Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoningcited by 85
  19. 2021Contrastive Explanations for Model Interpretabilitycited by 75
  20. 2021BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Beliefcited by 57
  21. 2020Consistency of a Recurrent Language Model With Respect to Incomplete Decodingcited by 54
  22. 2018Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledgecited by 46
  23. 2021COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentencescited by 40
  24. 2021Flexible Generation of Natural Language Deductionscited by 28
  25. 2020Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervisioncited by 27
  26. 2018What If We Simply Swap the Two Text Fragments? A Straightforward yet Effective Way to Test the Robustness of Methods to Confounding Signals in Nature Language Inference Taskscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 21; 2023: 68; 2024: 46; 2025: 18; 2026: 6.

159 papers.

Sort:

By area:

  1. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  2. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  3. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  4. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 767
  5. 2022Large Language Models Can Self-Improvecited by 664
  6. 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 619
  7. 2022Towards Reasoning in Large Language Models: A Surveycited by 596
  8. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  9. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 344
  10. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Trainingcited by 295
  11. 2023Faithful Chain-of-Thought Reasoningcited by 288
  12. 2022Reasoning with Language Model Prompting: A Surveycited by 252
38 more
  1. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 240
  2. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 238
  3. 2023Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Modelscited by 163
  4. 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 156
  5. 2022Ask Me Anything: A simple strategy for prompting language modelscited by 155
  6. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 130
  7. 2022A Survey of Deep Learning for Mathematical Reasoningcited by 124
  8. 2023Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselvescited by 123
  9. 2023Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!cited by 119
  10. 2022Teaching Algorithmic Reasoning via In-context Learningcited by 112
  11. 2022Rationale-Augmented Ensembles in Language Modelscited by 111
  12. 2023Question Decomposition Improves the Faithfulness of Model-Generated Reasoningcited by 108
  13. 2023Large Language Models as Analogical Reasonerscited by 107
  14. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 105
  15. 2023Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debatecited by 97
  16. 2023Cognitive Reframing of Negative Thoughts through Human-Language Model Interactioncited by 77
  17. 2024LLM-based NLG Evaluation: Current Status and Challengescited by 73
  18. 2022Complementary Explanations for Effective In-Context Learningcited by 71
  19. 2024Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?cited by 71
  20. 2023Applying Large Language Models and Chain-of-Thought for Automatic Scoringcited by 69
  21. 2023FELM: Benchmarking Factuality Evaluation of Large Language Modelscited by 66
  22. 2024A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chainscited by 65
  23. 2025Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Modelscited by 64
  24. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  25. 2023Towards Better Chain-of-Thought Prompting Strategies: A Surveycited by 62
  26. 2023Natural Language Reasoning, A Surveycited by 61
  27. 2023Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planningcited by 60
  28. 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalizationcited by 55
  29. 2025Empowering LLMs with Logical Reasoning: A Comprehensive Surveycited by 51
  30. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 50
  31. 2024A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Taskscited by 47
  32. 2023Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistencycited by 46
  33. 2024Process-Driven Autoformalization in Lean 4cited by 45
  34. 2023Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statementscited by 44
  35. 2023Benchmarking and Improving Generator-Validator Consistency of Language Modelscited by 44
  36. 2022Rainier: Reinforced Knowledge Introspector for Commonsense Question Answeringcited by 43
  37. 2023Prompting Large Language Models With the Socratic Methodcited by 43
  38. 2023Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agentscited by 41

50 most cited of 159 All 159 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Unbiased Reasoning for Knowledge-Intensive Tasks in Large Language Models via Conditional Front-Door Adjustment
  2. 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning
  3. 2026Benchmarking LLM Competence on Logical Inference over Probability Operators
  4. 2024How Interpretable are Reasoning Explanations from Prompting Large Language Models?
  5. 2023Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
  6. 2024Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?
  7. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning
  8. 2024C2P: Featuring Large Language Models with Causal Reasoning