模型即裁判论文趋势 2023–2026

主要结论

• 模型即裁判论文从 2023 年的 8 篇增长到 2026 年的 219 篇，三年间扩大到约 27 倍。
• NeurIPS 是发模型即裁判论文最多的会议，2023–2026 年共 173 篇，占四个会议总量的 43%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 78 篇。
• 在「评测与基准」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的大模型基准是 154 倍，模型即裁判是 27 倍。

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

• NeurIPS 2026A Free Lunch in LLM Compression: Revisiting Retraining after Pruning
• ICML 2026A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth
• ICLR 2026Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation
• CVPR 2026Pixels Dont Lie But Your Detector Might Bootstrapping MLLM-as-a-Judge for
• NeurIPS 2025$\texttt{BetaConform}$: Efficient MAP Estimation of LLM Ensemble Judgment Performance with Prior Transfer
• ICML 2025Active Evaluation Acquisition for Efficient LLM Benchmarking
• ICLR 2025An Empirical Analysis of Uncertainty in Large Language Model Evaluations
• CVPR 2025ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis
• NeurIPS 2024BertaQA: How Much Do Language Models Know About Local Culture?
• ICML 2024CHAI: Clustered Head Attention for Efficient LLM Inference
• ICLR 2024PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
• NeurIPS 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
• ICML 2023SAM operates far from home: eigenvalue regularization as a dynamical phenomenon
• ICLR 2023On the complexity of nonsmooth automatic differentiation
• NeurIPS 2026A Stratified Multi-Rater Evaluation of LLM-Based Virtual Standardized Patients with a Deployed Data-Generation Platform
• ICML 2026Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
• ICLR 2026AutoMetrics: Approximate Human Judgments with Automatically Generated Evaluators
• CVPR 20263DrawAgent Teaching LLM to Draw in 3D with Early Contrastive
• NeurIPS 2025Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees
• ICML 2025Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators

全部模型即裁判论文

共 126 篇，第 3 / 3 页

101. NeurIPS 2025Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning
102. NeurIPS 2025Masked Gated Linear Unit
103. NeurIPS 2025MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants
104. NeurIPS 2025metaTextGrad: Automatically optimizing language model optimizers
105. NeurIPS 2025MODEL SHAPLEY: Find Your Ideal Parameter Player via One Gradient Backpropagation
106. NeurIPS 2025MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search
107. NeurIPS 2025Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
108. NeurIPS 2025On Evaluating LLM Alignment by Evaluating LLMs as Judges
109. NeurIPS 2025PARALLELPROMPT: Extracting Parallelism from Large Language Model Queries
110. NeurIPS 2025Permissioned LLMs: Enforcing Access Control in Large Language Models
111. NeurIPS 2025Position: Benchmarking is Broken - Don't Let AI be Its Own Judge
112. NeurIPS 2025Predicting Empirical AI Research Outcomes with Language Models
113. NeurIPS 2025QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks
114. NeurIPS 2025Reparameterized LLM Training via Orthogonal Equivalence Transformation
115. NeurIPS 2025Reverse Engineering Human Preferences with Reinforcement Learning
116. NeurIPS 2025SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks
117. NeurIPS 2025Set-LLM: A Permutation-Invariant LLM
118. NeurIPS 2025SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
119. NeurIPS 2025The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias Optimization
120. NeurIPS 2025The Leaderboard Illusion
121. NeurIPS 2025The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement
122. NeurIPS 2025Towards Fully FP8 GEMM LLM Training at Scale
123. NeurIPS 2025Towards Reliable LLM-based Robots Planning via Combined Uncertainty Estimation
124. NeurIPS 2025URLs Help, Topics Guide: Understanding Metadata Utility in LLM Training
125. NeurIPS 2025Validating LLM-as-a-Judge Systems under Rating Indeterminacy
126. NeurIPS 2025Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator

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。