mlsanityData to 7 Oct 2026

CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing

arXiv 2305.11738 ↗First posted 19 May 2023cs.CL cs.AIcited by 751

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

Abstract (arXiv)

Recent developments in large language models (LLMs) have been impressive. However, these models sometimes show inconsistencies and problematic behavior, such as hallucinating facts, generating flawed code, or creating offensive and toxic content. Unlike these models, humans typically utilize external tools to cross-check and refine their initial content, like using a search engine for fact-checking, or a code interpreter for debugging. Inspired by this observation, we introduce a framework called CRITIC that allows LLMs, which are essentially "black boxes" to validate and progressively amend their own outputs in a manner similar to human interaction with tools. More specifically, starting with an initial output, CRITIC interacts with appropriate tools to evaluate certain aspects of the text, and then revises the output based on the feedback obtained during this validation process. Comprehensive evaluations involving free-form question answering, mathematical program synthesis, and toxicity reduction demonstrate that CRITIC consistently enhances the performance of LLMs. Meanwhile, our research highlights the crucial importance of external feedback in promoting the ongoing self-improvement of LLMs.

Key facts. Cited by 751 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 116 of its 144 references that are in the map. First posted on arXiv 19 May 2023.

Builds on

116 of 144 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023REFINER: Reasoning Feedback on Intermediate Representations4 Apr
  2. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar
  3. 2022Large Language Models Can Self-Improve20 Oct
  4. 2022Language Models (Mostly) Know What They Know11 Jul

Other references · 112

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  7. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  8. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  9. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  10. 2017On Calibration of Modern Neural Networkscited by 4,860
  11. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  12. 2017Deep reinforcement learning from human preferencescited by 3,846
38 more
  1. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  2. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  3. 2021Program Synthesis with Large Language Modelscited by 3,509
  4. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  5. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  7. 2020Learning to summarize from human feedbackcited by 2,562
  8. 2023A Survey of Large Language Modelscited by 2,537
  9. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  10. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  11. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  12. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  13. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  14. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  15. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  16. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  17. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  18. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  19. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  20. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  21. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  22. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  23. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  24. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
  25. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  26. 2019How Can We Know What Language Models Know?cited by 953
  27. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  28. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  29. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  30. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  31. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  32. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  33. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  34. 2022Galactica: A Large Language Model for Sciencecited by 736
  35. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  36. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  37. 2022PAL: Program-aided Language Modelscited by 635
  38. 2023Capabilities of GPT-4 on Medical Challenge Problemscited by 630

50 most cited of 112 All 112 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 63; 2024: 186; 2025: 217; 2026: 285.

751 papers.

Sort:

By area:

  1. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  3. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  4. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  5. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  6. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 483
  7. 2024Understanding the planning of LLM agents: A surveycited by 414
  8. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  9. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  10. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  11. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 293
  12. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 291
38 more
  1. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 276
  2. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 268
  3. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 257
  4. 2023Think before you speak: Training Language Models With Pause Tokenscited by 254
  5. 2023Challenges and Applications of Large Language Modelscited by 251
  6. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaborationcited by 246
  7. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 242
  8. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  9. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 230
  10. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 222
  11. 2024Tool Learning with Large Language Models: A Surveycited by 221
  12. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?cited by 215
  13. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 211
  14. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 206
  15. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  16. 2023Universal Self-Consistency for Large Language Model Generationcited by 198
  17. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  18. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  19. 2023OctoPack: Instruction Tuning Code Large Language Modelscited by 178
  20. 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improvecited by 162
  21. 2025The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoningcited by 160
  22. 2025Dynamic Cheatsheet: Test-Time Learning with Adaptive Memorycited by 146
  23. 2024Large Legal Fictions: Profiling Legal Hallucinations in Large Language Modelscited by 144
  24. 2023Factuality Challenges in the Era of Large Language Modelscited by 125
  25. 2024Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizingcited by 123
  26. 2023Chain of Code: Reasoning with a Language Model-Augmented Code Emulatorcited by 120
  27. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  28. 2024Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffoldingcited by 115
  29. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  30. 2023R-Tuning: Instructing Large Language Models to Say `I Don't Know'cited by 106
  31. 2024Critique-out-Loud Reward Modelscited by 105
  32. 2025AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?cited by 105
  33. 2024GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinementscited by 101
  34. 2024Chain of Thoughtlessness? An Analysis of CoT in Planningcited by 100
  35. 2023Shepherd: A Critic for Language Model Generationcited by 96
  36. 2023Let's reward step by step: Step-Level reward model as the Navigators for Reasoningcited by 96
  37. 2023Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revisioncited by 96
  38. 2025GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoningcited by 94

50 most cited of 751 All 751 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Self-Evolving Critique Abilities in Large Language Models
  2. 2025RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques
  3. 2025DeepCritic: Deliberate Critique with Large Language Models
  4. 2025CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models
  5. 2024Internal Consistency and Self-Feedback in Large Language Models: A Survey
  6. 2024Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models
  7. 2024Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
  8. 2025AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification