模型即裁判论文趋势 2023–2026

自动评测

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 401 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

模型即裁判论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202351208
202427129048
20255337333126
20268862645219

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部模型即裁判论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 401 篇，第 6 / 9 页

  1. ICLR 2025RMB: Comprehensively benchmarking reward models in LLM alignment
  2. ICLR 2025RocketEval: Efficient automated LLM evaluation via grading checklist
  3. ICLR 2025SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators
  4. ICLR 2025Selective Attention Improves Transformer
  5. ICLR 2025SpinQuant: LLM Quantization with Learned Rotations
  6. ICLR 2025SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget
  7. ICLR 2025Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking
  8. ICLR 2025ToolACE: Winning the Points of LLM Function Calling
  9. ICLR 2025Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement
  10. ICML 2025Accelerating Unbiased LLM Evaluation via Synthetic Feedback
  11. ICML 2025Active Evaluation Acquisition for Efficient LLM Benchmarking
  12. ICML 2025Agent-as-a-Judge: Evaluate Agents with Agents
  13. ICML 2025am-ELO: A Stable Framework for Arena-based LLM Evaluation
  14. ICML 2025Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle
  15. ICML 2025BaWA: Automatic Optimizing Pruning Metric for Large Language Models with Balanced Weight and Activation
  16. ICML 2025Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression
  17. ICML 2025Copilot Arena: A Platform for Code LLM Evaluation in the Wild
  18. ICML 2025CoSER: Coordinating LLM-Based Persona Simulation of Established Roles
  19. ICML 2025Demystifying Singular Defects in Large Language Models
  20. ICML 2025Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection
  21. ICML 2025Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators
  22. ICML 2025Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
  23. ICML 2025From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set
  24. ICML 2025Great Models Think Alike and this Undermines AI Oversight
  25. ICML 2025Investigating Non-Transitivity in LLM-as-a-Judge
  26. ICML 2025La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation
  27. ICML 2025Large Language-Geometry Model: When LLM meets Equivariance
  28. ICML 2025Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
  29. ICML 2025MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
  30. ICML 2025Memorization Sinks: Isolating Memorization during LLM Training
  31. ICML 2025Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design
  32. ICML 2025Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination’s Impact on Machine Translation
  33. ICML 2025Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints
  34. ICML 2025Position: LLM Social Simulations Are a Promising Research Method
  35. ICML 2025Position: Principles of Animal Cognition to Improve LLM Evaluations
  36. ICML 2025Position: The Most Expensive Part of an LLM *should* be its Training Data
  37. ICML 2025Prompt-to-Leaderboard: Prompt-Adaptive LLM Evaluations
  38. ICML 2025RZ-NAS: Enhancing LLM-guided Neural Architecture Search via Reflective Zero-Cost Strategy
  39. ICML 2025The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination
  40. ICML 2025Tuning LLM Judge Design Decisions for 1/1000 of the Cost
  41. ICML 2025TypyBench: Evaluating LLM Type Inference for Untyped Python Repositories
  42. ICML 2025Uncertainty Quantification for LLM-Based Survey Simulations
  43. NeurIPS 2025$\texttt{BetaConform}$: Efficient MAP Estimation of LLM Ensemble Judgment Performance with Prior Transfer
  44. NeurIPS 2025ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking
  45. NeurIPS 2025Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees
  46. NeurIPS 2025Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector
  47. NeurIPS 2025Ask a Strong LLM Judge when Your Reward Model is Uncertain
  48. NeurIPS 2025AutoJudge: Judge Decoding Without Manual Annotation
  49. NeurIPS 2025Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations
  50. NeurIPS 2025Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查模型即裁判在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "llm-as-judge"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇模型即裁判论文？
共 401 篇，按年份分别是 2023 年 8 篇、2024 年 48 篇、2025 年 126 篇、2026 年 219 篇。
NeurIPS 2026 有多少篇模型即裁判论文？
NeurIPS 2026 有 88 篇模型即裁判论文，上一届是 53 篇。
ICLR 2026 有多少篇模型即裁判论文？
ICLR 2026 有 62 篇模型即裁判论文，上一届是 37 篇。
ICML 2026 有多少篇模型即裁判论文？
ICML 2026 有 64 篇模型即裁判论文，上一届是 33 篇。
CVPR 2026 有多少篇模型即裁判论文？
CVPR 2026 有 5 篇模型即裁判论文，上一届是 3 篇。
哪个会议的模型即裁判论文最多？
NeurIPS，2023–2026 年共 173 篇。

「评测与基准」下的其他主题