人工评测论文趋势 2023–2026

人评协议

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 271 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

人工评测论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20239611733
20242511132170
20251716141360
202639292119108

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

全部人工评测论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 271 篇，第 4 / 6 页

  1. ICML 2025Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing
  2. NeurIPS 2025A Principled Path to Fitted Distributional Evaluation
  3. NeurIPS 2025AGENTIF: Benchmarking Large Language Models Instruction Following Ability in Agentic Scenarios
  4. NeurIPS 2025AI Debate Aids Assessment of Controversial Claims
  5. NeurIPS 2025Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations
  6. NeurIPS 2025Can Large Language Models Master Complex Card Games?
  7. NeurIPS 2025Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation
  8. NeurIPS 2025Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment
  9. NeurIPS 2025Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning
  10. NeurIPS 2025Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning
  11. NeurIPS 2025Don’t call it privacy-preserving or human-centric pose estimation if you don’t measure privacy
  12. NeurIPS 2025Handling Missing Responses under Cluster Dependence with Applications to Language Model Evaluation
  13. NeurIPS 2025Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization
  14. NeurIPS 2025Tackling Biased Evaluators in Dueling Bandits
  15. NeurIPS 2025Toward Human Deictic Gesture Target Estimation
  16. NeurIPS 2025Toward Interpretable Evaluation Measures for Time Series Segmentation
  17. NeurIPS 2025What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models
  18. NeurIPS 2025Words That Unite The World: A Unified Framework for Deciphering Central Bank Communications
  19. CVPR 20243D Human Pose Perception from Egocentric Stereo Videos
  20. CVPR 2024Can Biases in ImageNet Models Explain Generalization?
  21. CVPR 2024CG-HOI: Contact-Guided 3D Human-Object Interaction Generation
  22. CVPR 2024GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation
  23. CVPR 2024HIT: Estimating Internal Human Implicit Tissues from the Body Surface
  24. CVPR 2024HIVE: Harnessing Human Feedback for Instructional Visual Editing
  25. CVPR 2024HOIAnimator: Generating Text-prompt Human-object Animations using Novel Perceptive Diffusion Models
  26. CVPR 2024Inter-X: Towards Versatile Human-Human Interaction Analysis
  27. CVPR 2024Learning Multi-Dimensional Human Preference for Text-to-Image Generation
  28. CVPR 2024LEMON: Learning 3D Human-Object Interaction Relation from 2D Images
  29. CVPR 2024LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model
  30. CVPR 2024MaGGIe: Masked Guided Gradual Human Instance Matting
  31. CVPR 2024NECA: Neural Customizable Human Avatar
  32. CVPR 2024PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
  33. CVPR 2024Polos: Multimodal Metric Learning from Human Feedback for Image Captioning
  34. CVPR 2024Rethinking FID: Towards a Better Evaluation Metric for Image Generation
  35. CVPR 2024RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback
  36. CVPR 2024SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion
  37. CVPR 2024Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluation
  38. CVPR 2024TexVocab: Texture Vocabulary-conditioned Human Avatars
  39. CVPR 2024Towards a Perceptual Evaluation Framework for Lighting Estimation
  40. ICLR 2024Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
  41. ICLR 2024Does Writing with Language Models Reduce Content Diversity?
  42. ICLR 2024Evaluating Large Language Models at Evaluating Instruction Following
  43. ICLR 2024FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
  44. ICLR 2024Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained Models
  45. ICLR 2024Human Feedback is not Gold Standard
  46. ICLR 2024Identifying the Risks of LM Agents with an LM-Emulated Sandbox
  47. ICLR 2024MT-Ranker: Reference-free machine translation evaluation by inter-system ranking
  48. ICLR 2024On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMs
  49. ICLR 2024Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations
  50. ICLR 2024Unified Human-Scene Interaction via Prompted Chain-of-Contacts

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 查人工评测在 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": "human-evaluation"}

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。

「评测与基准」下的其他主题