mlsanityData to 7 Oct 2026

An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4

arXiv 2403.02839 ↗First posted 5 Mar 2024cs.CLcited by 90

Not on the map. Why?

Abstract (arXiv)

Recently, there has been a growing trend of utilizing Large Language Model (LLM) to evaluate the quality of other LLMs. Many studies have fine-tuned judge models based on open-source LLMs for evaluation. While the fine-tuned judge models are claimed to achieve comparable evaluation capability with GPT-4, in this work, we conduct an empirical study of LLM-as-a-Judge. Our findings indicate that although the fine-tuned judge models achieve high performance on in-domain test sets, even surpassing GPT-4, they underperform GPT-4 across several dimensions, including generalizability, fairness and adaptability. We also reveal that the fine-tuned judge model inherently operates as a task-specific classifier, consequently imposing the limitations.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). Builds on 22 of its 37 references that are in the map. First posted on arXiv 5 Mar 2024.

Builds on

22 of 37 references.

References · 22

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  6. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  7. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,718
  8. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  9. 2023LIMA: Less Is More for Alignmentcited by 1,080
  10. 2023Large Language Models are not Fair Evaluatorscited by 1,050
  11. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  12. 2022A Survey on In-context Learningcited by 717
10 more
  1. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 701
  2. 2023Prometheus: Inducing Fine-grained Evaluation Capability in Language Modelscited by 558
  3. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 486
  4. 2023JudgeLM: Fine-tuned Large Language Models are Scalable Judgescited by 351
  5. 2023PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimizationcited by 311
  6. 2023Evaluating Large Language Models at Evaluating Instruction Followingcited by 290
  7. 2023ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversationcited by 224
  8. 2019Probing Neural Network Comprehension of Natural Language Argumentscited by 212
  9. 2023Branch-Solve-Merge Improves Large Language Model Evaluation and Generationcited by 104
  10. 2023CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generationcited by 65

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 12; 2025: 39; 2026: 39.

90 papers.

Sort:

By area:

  1. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 451
  2. 2024Justice or Prejudice? Quantifying Biases in LLM-as-a-Judgecited by 354
  3. 2024Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Modelscited by 301
  4. 2024Large Language Models are Inconsistent and Biased Evaluatorscited by 146
  5. 2024Benchmark Data Contamination of Large Language Models: A Surveycited by 138
  6. 2024AutoEval Done Right: Using Synthetic Data for Model Evaluationcited by 53
  7. 2025Rating Roulette: Self-Inconsistency in LLM-As-A-Judge Frameworkscited by 37
  8. 2024Vibe-Eval: A hard evaluation suite for measuring progress of multimodal language modelscited by 35
  9. 2025How to Correctly Report LLM-as-a-Judge Evaluationscited by 25
  10. 2026Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judgescited by 23
  11. 2025Think-J: Learning to Think for Generative LLM-as-a-Judgecited by 20
  12. 2025TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Themcited by 20
38 more
  1. 2025Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queriescited by 16
  2. 2025Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Modelscited by 15
  3. 2025Is Relevance Propagated from Retriever to Generator in RAG?cited by 11
  4. 2025MedGUIDE: Benchmarking Clinical Decision-Making in Large Language Modelscited by 10
  5. 2025Automatically Benchmarking LLM Code Agents through Agent-Driven Annotation and Evaluationcited by 9
  6. 2026Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimizationcited by 8
  7. 2026When LLM Judge Scores Look Good but Best-of-N Decisions Failcited by 8
  8. 2026Reframing LLM Agent Security as an Agent-Human Interaction Problemcited by 8
  9. 2025Can LLMs Automate Fact-Checking Article Writing?cited by 7
  10. 2026PAIR-SAFE: A Paired-Agent Approach for Runtime Auditing and Refining AI-Mediated Mental Health Supportcited by 7
  11. 2026Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimizationcited by 7
  12. 2024VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoningcited by 6
  13. 2024Unveiling and Mitigating Bias in Large Language Model Recommendations: A Path to Fairnesscited by 6
  14. 2025Quantitative LLM Judgescited by 6
  15. 2025TURA: Tool-Augmented Unified Retrieval Agent for AI Searchcited by 6
  16. 2025Bridging Human and LLM Judgments: Understanding and Narrowing the Gapcited by 6
  17. 2025Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMscited by 6
  18. 2026Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judgecited by 6
  19. 2025DeepSeek-R1 vs. o3-mini: How Well can Reasoning LLMs Evaluate MT and Summarization?cited by 5
  20. 2025Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generationcited by 5
  21. 2025Evaluation Under Imperfect Benchmarks and Ratings: A Case Study in Text Simplificationcited by 4
  22. 2025Reference-Free Rating of LLM Responses via Latent Informationcited by 4
  23. 2026Bias and Uncertainty in LLM-as-a-Judge Estimationcited by 4
  24. 2024JurEE not Judges: safeguarding llm interactions with small, specialised Encoder Ensemblescited by 3
  25. 2025To Judge or not to Judge: Using LLM Judgements for Advertiser Keyphrase Relevance at eBaycited by 3
  26. 2025Reverse Engineering Human Preferences with Reinforcement Learningcited by 3
  27. 2025Towards EnergyGPT: A Large Language Model Specialized for the Energy Sectorcited by 3
  28. 2025ARCANE: A Multi-Agent Framework for Interpretable and Configurable Alignmentcited by 3
  29. 2026LLM Judges Can Be Too Generous When There Is No Reference Answercited by 3
  30. 2025MOAT: Evaluating LMMs for Capability Integration and Instruction Groundingcited by 2
  31. 2025Benchmarking Vision Language Models on German Factual Datacited by 2
  32. 2025VLM@school -- Evaluation of AI image understanding on German middle school knowledgecited by 2
  33. 2025PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimizationcited by 2
  34. 2025LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBaycited by 2
  35. 2025Reward Models are Metrics in a Trench Coatcited by 2
  36. 2025Learning a Single Token to Replace Long System Prompts in LLMscited by 2
  37. 2026Code Change Characteristics and Description Alignment: A Comparative Study of Agentic versus Human Pull Requestscited by 2
  38. 2026VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recoverycited by 2

50 most cited of 90 All 90 (JSON)