人工评测论文趋势 2023–2026

主要结论

• 人工评测论文从 2023 年的 33 篇增长到 2026 年的 108 篇，三年间扩大到约 3.3 倍。
• NeurIPS 是发人工评测论文最多的会议，2023–2026 年共 90 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是数据集与基准：同时属于两个主题的论文从 2023 年的 3 篇增至 2026 年的 31 篇。
• 在「评测与基准」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的大模型基准是 154 倍，人工评测是 3.3 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 2026Ad-Hoc Teamwork from Human Demonstrations
• ICML 2026SWE-IF: Aligning Code Evaluation with Human Preference
• ICLR 2026Human-LLM Collaborative Feature Engineering for Tabular Data
• CVPR 2026Bridging Human Evaluation to Infrared and Visible Image Fusion
• NeurIPS 2025Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning
• ICML 2025Position: When Incentives Backfire, Data Stops Being Human
• ICLR 2025Eliciting Human Preferences with Language Models
• CVPR 2025DynPose: Largely Improving the Efficiency of Human Pose Estimation by a Simple Dynamic Framework
• NeurIPS 2024DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA
• ICML 2024A Fine-grained Analysis of Fitted Q-evaluation: Beyond Parametric Models
• ICLR 2024Human Feedback is not Gold Standard
• CVPR 2024LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model
• NeurIPS 2023Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?
• ICML 2023Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts
• ICLR 2023Beyond calibration: estimating the grouping loss of modern neural networks
• CVPR 20233D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels
• NeurIPS 2026AI Construct Lexis: An Ontology of the Hidden Assumptions in AI Evaluation
• ICML 2026Rethinking Evaluation Paradigms in IBP-based Certified Training
• ICLR 2026Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models
• CVPR 2026Ground Reaction Inertial Poser Physics-based Human Motion Capture from Sparse

全部人工评测论文

共 90 篇，第 1 / 2 页

1. NeurIPS 2026Ad-Hoc Teamwork from Human Demonstrations
2. NeurIPS 2026AI Construct Lexis: An Ontology of the Hidden Assumptions in AI Evaluation
3. NeurIPS 2026AIRA 2: Overcoming Bottlenecks in AI Research Agents
4. NeurIPS 2026AMUSE: Anytime Muon with Stable Gradient Evaluation
5. NeurIPS 2026An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models
6. NeurIPS 2026BayesJudge: Uncertainty-Aware Bayesian Meta-Evaluation of Human and LLM Judgments
7. NeurIPS 2026BenchRep-T: A Systematic Evaluation of T-Cell Repertoire-Based Disease Diagnostics
8. NeurIPS 2026Beyond Proxy Metrics: MLLM-Based Human Surrogate Evaluation for Explainable AI
9. NeurIPS 2026Correct, Route, Calibrate: Efficient Preference Optimization from Noisy, Heterogeneous Human Feedback
10. NeurIPS 2026Cosine is Human: The Reproducibility Ceiling of Perceptual Similarity
11. NeurIPS 2026Evaluating an Evaluation: Membership Inference Attacks as Machine Unlearning Diagnostics
12. NeurIPS 2026Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered
13. NeurIPS 2026From Uncertain Judgments to Calibrated Rankings: Conformal Elo Estimation for LLM Evaluation
14. NeurIPS 2026General Agent Evaluation
15. NeurIPS 2026GT-Free OCR Metrics: A Reference-Free Evaluation Framework for Document OCR Systems
16. NeurIPS 2026Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
17. NeurIPS 2026HearSayBench: Can LLMs Navigate from Abstract Human Rights to Lived Lives?
18. NeurIPS 2026HERO: Improving the Reliability and Sensitivity of Generative Model Evaluation Using Historical Data
19. NeurIPS 2026ImageNet FID is a Pass Check, Not a Finish Line
20. NeurIPS 2026Intra-Option Fitted Q-Evaluation: Evaluating Hierarchical Policies from Non-Hierarchical Data
21. NeurIPS 2026Leak-CURBER: A Leakage-Controlled Multimodal Evaluation Benchmark for Enzymatic Reaction Tasks
22. NeurIPS 2026OdysSim: Building Foundation Models for Human Behavior Simulation
23. NeurIPS 2026Off-Policy Evaluation of Large Language Models via Learned Semantic Bottleneck Embeddings
24. NeurIPS 2026OmniMechanism Design for Human-AI Collaboration with Impressionable Minds
25. NeurIPS 2026OTROPE: Optimal Transport-based Robust Off-policy Evaluation for Large Language Models
26. NeurIPS 2026PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos
27. NeurIPS 2026Post-Selection Distributional Model Evaluation
28. NeurIPS 2026pyCD: A Unified Benchmark for Reliable Evaluation of Cognitive Diagnosis Models
29. NeurIPS 2026Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation
30. NeurIPS 2026Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settings
31. NeurIPS 2026SALART-VQA: Diagnosing Whether VLMs Understand Salient Artifacts in Generated Images
32. NeurIPS 2026Select Smarter, Not More? Prompt-Aware Evaluation Scheduling with Submodular Guarantees
33. NeurIPS 2026SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation
34. NeurIPS 2026The Deadline Effect: Identifying and Correcting Temporal Bias in Human Evaluation
35. NeurIPS 2026Verifier Choice is a Benchmark Design Variable: Auditing Structural Counting Evaluation in Text-to-Image Models
36. NeurIPS 2026VIPBench: A Human-Aligned Benchmark for Voice Identity Perception in the Age of Voice Cloning
37. NeurIPS 2026VTBench: Disentangled and Human-Aligned Evaluation for Image-Based Virtual Try-on
38. NeurIPS 2026When Are Predictions Enough? An Evaluation Protocol for Frozen Expert Composition
39. NeurIPS 2026WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
40. NeurIPS 2025A Principled Path to Fitted Distributional Evaluation
41. NeurIPS 2025AGENTIF: Benchmarking Large Language Models Instruction Following Ability in Agentic Scenarios
42. NeurIPS 2025AI Debate Aids Assessment of Controversial Claims
43. NeurIPS 2025Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations
44. NeurIPS 2025Can Large Language Models Master Complex Card Games?
45. NeurIPS 2025Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation
46. NeurIPS 2025Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment
47. NeurIPS 2025Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning
48. NeurIPS 2025Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning
49. NeurIPS 2025Don’t call it privacy-preserving or human-centric pose estimation if you don’t measure privacy
50. NeurIPS 2025Handling Missing Responses under Cluster Dependence with Applications to Language Model Evaluation

常见问题

2023–2026 年四大会议一共有多少篇人工评测论文？

共 271 篇，按年份分别是 2023 年 33 篇、2024 年 70 篇、2025 年 60 篇、2026 年 108 篇。

NeurIPS 2026 有多少篇人工评测论文？

NeurIPS 2026 有 39 篇人工评测论文，上一届是 17 篇。

ICLR 2026 有多少篇人工评测论文？

ICLR 2026 有 29 篇人工评测论文，上一届是 16 篇。

ICML 2026 有多少篇人工评测论文？

ICML 2026 有 21 篇人工评测论文，上一届是 14 篇。

CVPR 2026 有多少篇人工评测论文？

CVPR 2026 有 19 篇人工评测论文，上一届是 13 篇。

哪个会议的人工评测论文最多？

NeurIPS，2023–2026 年共 90 篇。