mlsanityData to 7 Oct 2026

CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation

arXiv 2311.18702 ↗First posted 30 Nov 2023cs.CL cs.AIcited by 65

Not on the map. Why?

Abstract (arXiv)

Since the natural language processing (NLP) community started to make large language models (LLMs) act as a critic to evaluate the quality of generated texts, most of the existing works train a critique generation model on the evaluation data labeled by GPT-4's direct prompting. We observe that these models lack the ability to generate informative critiques in both pointwise grading and pairwise comparison especially without references. As a result, their generated critiques cannot provide fine-grained distinguishability on generated texts, causing unsatisfactory evaluation performance. In this paper, we propose a simple yet effective method called Eval-Instruct, which can first acquire pointwise grading critiques with pseudo references and then revise these critiques via multi-path prompting to obtain informative evaluation data in different tasks and settings, including pointwise grading and pairwise comparison with / without references. After fine-tuning on these data, the resulting model CritiqueLLM is empirically shown to outperform ChatGPT and all the open-source baselines and even achieve comparable evaluation performance to GPT-4 in system-level correlations of pointwise grading. We also demonstrate that our generated critiques can act as scalable feedback to further improve the generation quality of strong LLMs like ChatGPT.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). Builds on 30 of its 50 references that are in the map. First posted on arXiv 30 Nov 2023.

Builds on

30 of 50 references.

References · 30

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2023Qwen Technical Reportcited by 3,273
  7. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  9. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  10. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  11. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  12. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
18 more
  1. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  2. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  3. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
  4. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 701
  5. 2023C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Modelscited by 694
  6. 2023Baichuan 2: Open Large-scale Language Modelscited by 664
  7. 2023Is ChatGPT a Good NLG Evaluator? A Preliminary Studycited by 420
  8. 2023PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimizationcited by 311
  9. 2020Evaluation of Text Generation: A Surveycited by 275
  10. 2022ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoningcited by 175
  11. 2023A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasetscited by 123
  12. 2023Can Large Language Models Really Improve by Self-critiquing Their Own Plans?cited by 107
  13. 2023Shepherd: A Critic for Language Model Generationcited by 96
  14. 2023GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problemscited by 88
  15. 2022On the Blind Spots of Model-Based Evaluation Metrics for Text Generationcited by 48
  16. 2023Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysiscited by 34
  17. 2021InfoLM: A New Metric to Evaluate Summarization & Data2Text Generationcited by 33
  18. 2023DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answeringcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 12; 2025: 36; 2026: 17.

65 papers.

Sort:

By area:

  1. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 480
  2. 2024Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinementcited by 111
  3. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 96
  4. 2024An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4cited by 90
  5. 2025Safety in Large Reasoning Models: A Surveycited by 58
  6. 2025Evaluating Scoring Bias in LLM-as-a-Judgecited by 42
  7. 2025Neither Valid nor Reliable? Investigating the Use of LLMs as Judgescited by 37
  8. 2024metabench -- A Sparse Benchmark of Reasoning and Knowledge in Large Language Modelscited by 35
  9. 2024LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraintscited by 34
  10. 2025CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Taskscited by 32
  11. 2025Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thoughtcited by 28
  12. 2025Think-J: Learning to Think for Generative LLM-as-a-Judgecited by 20
38 more
  1. 2025CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarioscited by 19
  2. 2024What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluationcited by 17
  3. 2025DeepCritic: Deliberate Critique with Large Language Modelscited by 17
  4. 2025R4ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systemscited by 16
  5. 2025CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Modelscited by 14
  6. 2025Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critiquecited by 13
  7. 2025Generative RLHF-V: Learning Principles from Multi-modal Human Preferencecited by 13
  8. 2025HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistantscited by 10
  9. 2024Measuring Psychological Depth in Language Modelscited by 9
  10. 2025Training an LLM-as-a-Judge Model: Pipeline, Insights, and Practical Lessonscited by 9
  11. 2025What do Large Language Models Say About Animals? Investigating Risks of Animal Harm in Generated Textcited by 9
  12. 2025Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contextscited by 9
  13. 2025Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learningcited by 9
  14. 2025VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generationcited by 8
  15. 2026Ad Insertion in LLM-Generated Responsescited by 8
  16. 2026AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applicationscited by 8
  17. 2025Training Language Model to Critique for Better Refinementcited by 7
  18. 2025Quantitative LLM Judgescited by 6
  19. 2025HPSS: Heuristic Prompting Strategy Search for LLM Evaluatorscited by 5
  20. 2025Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generationcited by 5
  21. 2025Auto-Prompt Ensemble for LLM Judgecited by 5
  22. 2025IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluationcited by 4
  23. 2024EVA-Score: Evaluating Abstractive Long-form Summarization on Informativeness through Extraction and Validationcited by 3
  24. 2025Diagnosing Failures in Large Language Models' Answers: Integrating Error Attribution into Evaluation Frameworkcited by 3
  25. 2026Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewardscited by 3
  26. 2024LUK: Empowering Log Understanding with Expert Knowledge from Large Language Modelscited by 2
  27. 2024The Superalignment of Superhuman Intelligence with Large Language Modelscited by 2
  28. 2025What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effectscited by 2
  29. 2025Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoningcited by 2
  30. 2024Closing the Loop: Learning to Generate Writing Feedback via Language Model Simulated Student Revisionscited by 1
  31. 2025A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretabilitycited by 1
  32. 2025Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMscited by 1
  33. 2025Enhanced Question-Answering for Skill-based learning using Knowledge-based AI and Generative AIcited by 1
  34. 2025LecEval: An Automated Metric for Multimodal Knowledge Acquisition in Multimedia Learningcited by 1
  35. 2025RRTL: Red Teaming Reasoning Large Language Models in Tool Learningcited by 1
  36. 2026From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimizationcited by 1
  37. 2026RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Modelscited by 1
  38. 2026HoWToBench: Holistic Evaluation for LLM's Capability in Human-level Writing using Tree of Writingcited by 1

50 most cited of 65 All 65 (JSON)