mlsanityData to 7 Oct 2026

SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning

arXiv 2308.00436 ↗First posted 1 Aug 2023cs.AI cs.CL cs.LGcited by 157

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

The recent progress in large language models (LLMs), especially the invention of chain-of-thought prompting, has made it possible to automatically answer questions by stepwise reasoning. However, when faced with more complicated problems that require non-linear thinking, even the strongest LLMs make mistakes. To address this, we explore whether LLMs are able to recognize errors in their own step-by-step reasoning, without resorting to external resources. To this end, we propose SelfCheck, a general-purpose zero-shot verification schema for recognizing such errors. We then use the results of these checks to improve question-answering performance by conducting weighted voting on multiple solutions to the question. We test SelfCheck on three datasets (GSM8K, MathQA, and MATH) and find that it successfully recognizes errors and, in turn, increases final answer accuracies.

Key facts. Cited by 157 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 19 of its 24 references that are in the map. First posted on arXiv 1 Aug 2023.

Builds on

19 of 24 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023REFINER: Reasoning Feedback on Intermediate Representations4 Apr

Other references · 18

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  8. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  9. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  10. 2023Let's Verify Step by Stepcited by 3,598
  11. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  12. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
6 more
  1. 2023PaLM 2 Technical Reportcited by 1,154
  2. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 653
  3. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  4. 2023Faithful Chain-of-Thought Reasoningcited by 285
  5. 2023Deductive Verification of Chain-of-Thought Reasoningcited by 122
  6. 2023Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performancecited by 102

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 18; 2024: 62; 2025: 52; 2026: 25.

157 papers.

Sort:

By area:

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  3. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  4. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 317
  5. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  6. 2024ReFT: Reasoning with Reinforced Fine-Tuningcited by 236
  7. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 230
  8. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 226
  9. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  10. 2025Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systemscited by 170
  11. 2024O1 Replication Journey: A Strategic Progress Report -- Part 1cited by 140
  12. 2023AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systemscited by 116
38 more
  1. 2025Confidence Improves Self-Consistency in LLMscited by 111
  2. 2023LLMs cannot find reasoning errors, but can correct them given the error locationcited by 85
  3. 2024Formal Mathematical Reasoning: A New Frontier in AIcited by 80
  4. 2024Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphscited by 77
  5. 2024Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Samplingcited by 63
  6. 2024The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Modelscited by 62
  7. 2025Hume: Introducing System-2 Thinking in Visual-Language-Action Modelcited by 56
  8. 2024Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideascited by 52
  9. 2024Evaluating LLMs at Detecting Errors in LLM Responsescited by 49
  10. 2024Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Eracited by 45
  11. 2023A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoningcited by 41
  12. 2024Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Modelscited by 41
  13. 2024Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflectioncited by 40
  14. 2024Large Language Models Can Self-Correct with Key Condition Verificationcited by 39
  15. 2024Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characterscited by 39
  16. 2024m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Taskscited by 38
  17. 2024Self-Reflection in LLM Agents: Effects on Problem-Solving Performancecited by 38
  18. 2024Knowledge Boundary of Large Language Models: A Surveycited by 36
  19. 2024SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correctioncited by 32
  20. 2024Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Modelscited by 31
  21. 2024Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuningcited by 30
  22. 2023DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planningcited by 28
  23. 2024Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolutioncited by 28
  24. 2024LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thoughtcited by 28
  25. 2024A Survey of Useful LLM Evaluationcited by 28
  26. 2024LLM-Empowered State Representation for Reinforcement Learningcited by 28
  27. 2024Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generationcited by 27
  28. 2023Mathematical Language Models: A Surveycited by 24
  29. 2024Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoningcited by 24
  30. 2024AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decompositioncited by 24
  31. 2024Attention Prompting on Image for Large Vision-Language Modelscited by 23
  32. 2024Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimizationcited by 22
  33. 2024Improving Physics Reasoning in Large Language Models Using Mixture of Refinement Agentscited by 22
  34. 2025Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuningcited by 21
  35. 2024DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Modelscited by 20
  36. 2025CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thoughtcited by 20
  37. 2025Frontier LLMs Still Struggle with Simple Reasoning Taskscited by 20
  38. 2024Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Coursecited by 19

50 most cited of 157 All 157 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022Large Language Models are Better Reasoners with Self-Verification
  2. 2025Zero-Shot Verification-guided Chain of Thoughts
  3. 2022Large Language Models Can Self-Improve
  4. 2025Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
  5. 2025Incentivizing LLMs to Self-Verify Their Answers
  6. 2025The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding?
  7. 2025Asking LLMs to Verify First is Almost Free Lunch
  8. 2024Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning