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 62 篇，第 1 / 2 页

1. ICLR 2026AutoLibra: Agent Metric Induction from Open-Ended Human Feedback
2. ICLR 2026AutoMetrics: Approximate Human Judgments with Automatically Generated Evaluators
3. ICLR 2026Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation
4. ICLR 2026Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration
5. ICLR 2026CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering
6. ICLR 2026Death of the Novel(ty): Beyond N-Gram Novelty as a Metric for Textual Creativity
7. ICLR 2026Direct Reward Fine-Tuning on Poses for Single Image to 3D Human in the Wild
8. ICLR 2026ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM Framework
9. ICLR 2026How NOT to benchmark your SITE metric: Beyond Static Leaderboards and Towards Realistic Evaluation.
10. ICLR 2026Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction
11. ICLR 2026Human-LLM Collaborative Feature Engineering for Tabular Data
12. ICLR 2026Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models
13. ICLR 2026HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes
14. ICLR 2026HUME: Measuring the Human-Model Performance Gap in Text Embedding Tasks
15. ICLR 2026LFQA-E: Carefully Benchmarking Long-form QA Evaluation
16. ICLR 2026M4PQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluation
17. ICLR 2026MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling
18. ICLR 2026Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models
19. ICLR 2026Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges
20. ICLR 2026Quantum machine learning advantages beyond hardness of evaluation
21. ICLR 2026ROSETTA: Constructing Code-Based Reward from Unconstrained Language Preference
22. ICLR 2026Scalable Oversight via Partitioned Human Supervision
23. ICLR 2026SEED: Towards More Accurate Semantic Evaluation for Visual Brain Decoding
24. ICLR 2026SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verification
25. ICLR 2026Systematic Biosafety Evaluation of DNA Language Models under Jailbreak Attacks
26. ICLR 2026The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas
27. ICLR 2026The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?
28. ICLR 2026Theory-Grounded Evaluation of Human-Like Fallacy Patterns in LLM Reasoning
29. ICLR 2026Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework
30. ICLR 2025An Empirical Analysis of Uncertainty in Large Language Model Evaluations
31. ICLR 2025Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge
32. ICLR 2025Consistency Checks for Language Model Forecasters
33. ICLR 2025DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation
34. ICLR 2025Eliciting Human Preferences with Language Models
35. ICLR 2025Human Simulacra: Benchmarking the Personification of Large Language Models
36. ICLR 2025Human-Aligned Chess With a Bit of Search
37. ICLR 2025Inverse Constitutional AI: Compressing Preferences into Principles
38. ICLR 2025Language Models Learn to Mislead Humans via RLHF
39. ICLR 2025Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation
40. ICLR 2025On Speeding Up Language Model Evaluation
41. ICLR 2025Realistic Evaluation of Deep Partial-Label Learning Algorithms
42. ICLR 2025Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?
43. ICLR 2025RevisEval: Improving LLM-as-a-Judge via Response-Adapted References
44. ICLR 2025Revisiting text-to-image evaluation with Gecko: on metrics, prompts, and human rating
45. ICLR 2025Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement
46. ICLR 2024Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
47. ICLR 2024Does Writing with Language Models Reduce Content Diversity?
48. ICLR 2024Evaluating Large Language Models at Evaluating Instruction Following
49. ICLR 2024FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
50. ICLR 2024Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained Models

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。