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 37 篇，第 1 / 1 页

  1. ICLR 2025A Statistical Framework for Ranking LLM-based Chatbots
  2. ICLR 2025AgentSquare: Automatic LLM Agent Search in Modular Design Space
  3. ICLR 2025An Empirical Analysis of Uncertainty in Large Language Model Evaluations
  4. ICLR 2025BadJudge: Backdoor Vulnerabilities of LLM-As-A-Judge
  5. ICLR 2025Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback
  6. ICLR 2025Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge
  7. ICLR 2025Catastrophic Failure of LLM Unlearning via Quantization
  8. ICLR 2025Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates
  9. ICLR 2025Combatting Dimensional Collapse in LLM Pre-Training Data via Submodular File Selection
  10. ICLR 2025Controlled LLM Decoding via Discrete Auto-regressive Biasing
  11. ICLR 2025Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents
  12. ICLR 2025Do LLMs have Consistent Values?
  13. ICLR 2025GraphEval: A Lightweight Graph-Based LLM Framework for Idea Evaluation
  14. ICLR 2025HShare: Fast LLM Decoding by Hierarchical Key-Value Sharing
  15. ICLR 2025Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
  16. ICLR 2025JudgeBench: A Benchmark for Evaluating LLM-Based Judges
  17. ICLR 2025Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
  18. ICLR 2025Language Model Alignment in Multilingual Trolley Problems
  19. ICLR 2025Language Models Are Implicitly Continuous
  20. ICLR 2025Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation
  21. ICLR 2025Learning LLM-as-a-Judge for Preference Alignment
  22. ICLR 2025Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the data
  23. ICLR 2025LiveBench: A Challenging, Contamination-Limited LLM Benchmark
  24. ICLR 2025On Calibration of LLM-based Guard Models for Reliable Content Moderation
  25. ICLR 2025Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages
  26. ICLR 2025Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models
  27. ICLR 2025Progressive Mixed-Precision Decoding for Efficient LLM Inference
  28. ICLR 2025RevisEval: Improving LLM-as-a-Judge via Response-Adapted References
  29. ICLR 2025RMB: Comprehensively benchmarking reward models in LLM alignment
  30. ICLR 2025RocketEval: Efficient automated LLM evaluation via grading checklist
  31. ICLR 2025SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators
  32. ICLR 2025Selective Attention Improves Transformer
  33. ICLR 2025SpinQuant: LLM Quantization with Learned Rotations
  34. ICLR 2025SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget
  35. ICLR 2025Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking
  36. ICLR 2025ToolACE: Winning the Points of LLM Function Calling
  37. ICLR 2025Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement

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