mlsanityData to 14 Oct 2026

Generative Judge for Evaluating Alignment

arXiv 2310.05470 ↗First posted 9 Oct 2023cs.CL cs.AIcited by 169

Not on the map. Why?

Cited by 47 in LLM alignment / RLHF / preference optimisation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The rapid development of Large Language Models (LLMs) has substantially expanded the range of tasks they can address. In the field of Natural Language Processing (NLP), researchers have shifted their focus from conventional NLP tasks (e.g., sequence tagging and parsing) towards tasks that revolve around aligning with human needs (e.g., brainstorming and email writing). This shift in task distribution imposes new requirements on evaluating these aligned models regarding generality (i.e., assessing performance across diverse scenarios), flexibility (i.e., examining under different protocols), and interpretability (i.e., scrutinizing models with explanations). In this paper, we propose a generative judge with 13B parameters, Auto-J, designed to address these challenges. Our model is trained on user queries and LLM-generated responses under massive real-world scenarios and accommodates diverse evaluation protocols (e.g., pairwise response comparison and single-response evaluation) with well-structured natural language critiques. To demonstrate the efficacy of our approach, we construct a new testbed covering 58 different scenarios. Experimentally, Auto-J outperforms a series of strong competitors, including both open-source and closed-source models, by a large margin. We also provide detailed analysis and case studies to further reveal the potential of our method and make a variety of resources public at https://github.com/GAIR-NLP/auto-j.

Key facts. Cited by 169 papers in the map (data through 14 Oct 2026). Builds on 41 of its 60 references that are in the map. First posted on arXiv 9 Oct 2023.

Builds on

41 of 60 references.

References · 41

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2022Training language models to follow instructions with human feedbackcited by 15,971
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  7. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  8. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  9. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  10. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  11. 2023Let's Verify Step by Stepcited by 3,789
  12. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
29 more
  1. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  2. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  3. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  5. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
  6. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  7. 2020Learning to summarize from human feedbackcited by 2,588
  8. 2018Deep contextualized word representationscited by 2,290
  9. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  10. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  11. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  12. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,125
  13. 2023LIMA: Less Is More for Alignmentcited by 1,100
  14. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,095
  15. 2023Large Language Models are not Fair Evaluatorscited by 1,085
  16. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 860
  17. 2016Training Deep Nets with Sublinear Memory Costcited by 848
  18. 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedbackcited by 748
  19. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 722
  20. 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignmentcited by 721
  21. 2022Self-critiquing models for assisting human evaluatorscited by 380
  22. 2023GPTScore: Evaluate as You Desirecited by 361
  23. 2021ZeRO-Offload: Democratizing Billion-Scale Model Trainingcited by 341
  24. 2023PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimizationcited by 316
  25. 2021Understanding Dataset Difficulty with V-Usable Informationcited by 291
  26. 2020Re-evaluating Evaluation in Text Summarizationcited by 145
  27. 2023Shepherd: A Critic for Language Model Generationcited by 97
  28. 2023Wider and Deeper LLM Networks are Fairer LLM Evaluatorscited by 94
  29. 2015Better Summarization Evaluation with Word Embeddings for ROUGEcited by 66

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 51; 2025: 73; 2026: 41.

169 papers.

Sort:

By area:

  1. 2024RewardBench: Evaluating Reward Models for Language Modelingcited by 499
  2. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 465
  3. 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmarkcited by 372
  4. 2023JudgeLM: Fine-tuned Large Language Models are Scalable Judgescited by 367
  5. 2024JudgeBench: A Benchmark for Evaluating LLM-based Judgescited by 318
  6. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 284
  7. 2025Improving Video Generation with Human Feedbackcited by 284
  8. 2024Self-Play Preference Optimization for Language Model Alignmentcited by 232
  9. 2024Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judgescited by 205
  10. 2024Advancing LLM Reasoning Generalists with Preference Treescited by 192
  11. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  12. 2024Optimization-based Prompt Injection Attack to LLM-as-a-Judgecited by 143
38 more
  1. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 111
  2. 2024Critique-out-Loud Reward Modelscited by 106
  3. 2024The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Modelscited by 93
  4. 2023Alignment for Honestycited by 74
  5. 2024LLM-based NLG Evaluation: Current Status and Challengescited by 73
  6. 2024Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templatescited by 72
  7. 2024Self-Generated Critiques Boost Reward Modeling for Language Modelscited by 71
  8. 2025A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Futurecited by 53
  9. 2025Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewardscited by 50
  10. 2024Improving Reward Models with Synthetic Critiquescited by 44
  11. 2025Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluatorscited by 44
  12. 2024CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolutioncited by 42
  13. 2025CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Rewardcited by 40
  14. 2025Neither Valid nor Reliable? Investigating the Use of LLMs as Judgescited by 39
  15. 2025LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judgecited by 37
  16. 2025Play Favorites: A Statistical Method to Measure Self-Bias in LLM-as-a-Judgecited by 36
  17. 2024Evaluating the Evaluator: Measuring LLMs' Adherence to Task Evaluation Instructionscited by 34
  18. 2024Direct Judgement Preference Optimizationcited by 33
  19. 2025CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Taskscited by 33
  20. 2024Beyond Scalar Reward Model: Learning Generative Judge from Preference Datacited by 32
  21. 2025Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward Modelingcited by 30
  22. 2024Prediction-Powered Ranking of Large Language Modelscited by 29
  23. 2025Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarkscited by 28
  24. 2024A Survey on Human Preference Learning for Large Language Modelscited by 24
  25. 2025SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reductioncited by 24
  26. 2024Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Surveycited by 23
  27. 2024CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responsescited by 23
  28. 2025Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judgecited by 23
  29. 2024JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuitcited by 22
  30. 2025Think-J: Learning to Think for Generative LLM-as-a-Judgecited by 21
  31. 2024DialSim: A Dialogue Simulator for Evaluating Long-Term Multi-Party Dialogue Understanding of Conversational Agentscited by 20
  32. 2024RevisEval: Improving LLM-as-a-Judge via Response-Adapted Referencescited by 20
  33. 2025TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Themcited by 20
  34. 2024xFinder: Large Language Models as Automated Evaluators for Reliable Evaluationcited by 19
  35. 2024Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competitioncited by 18
  36. 2024Position: Towards Bidirectional Human-AI Alignmentcited by 18
  37. 2025Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorerscited by 18
  38. 2024Natural Language Reinforcement Learningcited by 17

50 most cited of 169 All 169 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025On Evaluating LLM Alignment by Evaluating LLMs as Judges
  2. 2023Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks
  3. 2026LLM as a Meta-Judge: Synthetic Data for NLP Evaluation Metric Validation
  4. 2023Aligning Large Language Models with Human: A Survey
  5. 2025Aligning Black-box Language Models with Human Judgments
  6. 2023TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMs
  7. 2025The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs
  8. 2026BabelJudge: Measuring LLM-as-a-Judge Reliability Across Languages and Agent Trajectories