信息抽取论文趋势 2023–2026

NER、关系与事件抽取

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 798 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

信息抽取论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202344264627143
202467366522190
202580504623199
202696637433266

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

全部信息抽取论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 798 篇，第 12 / 16 页

  1. ICML 2024Leveraging (Biased) Information: Multi-armed Bandits with Offline Data
  2. ICML 2024Localizing Task Information for Improved Model Merging and Compression
  3. ICML 2024MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspective
  4. ICML 2024Matrix Information Theory for Self-Supervised Learning
  5. ICML 2024Mitigating Label Noise on Graphs via Topological Sample Selection
  6. ICML 2024No Free Prune: Information-Theoretic Barriers to Pruning at Initialization
  7. ICML 2024Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation
  8. ICML 2024Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs
  9. ICML 2024Performance Bounds for Active Binary Testing with Information Maximization
  10. ICML 2024Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
  11. ICML 2024Pi-DUAL: Using privileged information to distinguish clean from noisy labels
  12. ICML 2024Prospective Side Information for Latent MDPs
  13. ICML 2024Reinforcement Learning from Reachability Specifications: PAC Guarantees with Expected Conditional Distance
  14. ICML 2024Repeat After Me: Transformers are Better than State Space Models at Copying
  15. ICML 2024Rethinking Guidance Information to Utilize Unlabeled Samples: A Label Encoding Perspective
  16. ICML 2024RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning
  17. ICML 2024RMIB: Representation Matching Information Bottleneck for Matching Text Representations
  18. ICML 2024S$\Omega$I: Score-based O-INFORMATION Estimation
  19. ICML 2024Safe and Robust Subgame Exploitation in Imperfect Information Games
  20. ICML 2024Sequential Disentanglement by Extracting Static Information From A Single Sequence Element
  21. ICML 2024Slicing Mutual Information Generalization Bounds for Neural Networks
  22. ICML 2024Sliding Down the Stairs: How Correlated Latent Variables Accelerate Learning with Neural Networks
  23. ICML 2024Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach
  24. ICML 2024State-Constrained Zero-Sum Differential Games with One-Sided Information
  25. ICML 2024Stealing part of a production language model
  26. ICML 2024Stochastic Interpolants with Data-Dependent Couplings
  27. ICML 2024Surface-VQMAE: Vector-quantized Masked Auto-encoders on Molecular Surfaces
  28. ICML 2024The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents
  29. ICML 2024The Fundamental Limits of Least-Privilege Learning
  30. ICML 2024TimeX++: Learning Time-Series Explanations with Information Bottleneck
  31. ICML 2024Towards Generalization beyond Pointwise Learning: A Unified Information-theoretic Perspective
  32. ICML 2024Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot
  33. ICML 2024Understanding Finetuning for Factual Knowledge Extraction
  34. ICML 2024Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training
  35. ICML 2024Unveiling the Dynamics of Information Interplay in Supervised Learning
  36. ICML 2024USTAD: Unified Single-model Training Achieving Diverse Scores for Information Retrieval
  37. ICML 2024Visual Transformer with Differentiable Channel Selection: An Information Bottleneck Inspired Approach
  38. ICML 2024Weisfeiler-Leman at the margin: When more expressivity matters
  39. NeurIPS 2024A Benchmark Suite for Evaluating Neural Mutual Information Estimators on Unstructured Datasets
  40. NeurIPS 2024Accelerating Relative Entropy Coding with Space Partitioning
  41. NeurIPS 2024Adaptive Passive-Aggressive Framework for Online Regression with Side Information
  42. NeurIPS 2024An Information Theoretic Perspective on Conformal Prediction
  43. NeurIPS 2024Approximating mutual information of high-dimensional variables using learned representations
  44. NeurIPS 2024Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
  45. NeurIPS 2024Beyond Slow Signs in High-fidelity Model Extraction
  46. NeurIPS 2024Bootstrapping Top-down Information for Self-modulating Slot Attention
  47. NeurIPS 2024Bridging semantics and pragmatics in information-theoretic emergent communication
  48. NeurIPS 2024CIFD: Controlled Information Flow to Enhance Knowledge Distillation
  49. NeurIPS 2024Continuous Spatiotemporal Events Decoupling through Spike-based Bayesian Computation
  50. NeurIPS 2024Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

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 查信息抽取在 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": "information-extraction"}

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信息抽取论文？
共 798 篇，按年份分别是 2023 年 143 篇、2024 年 190 篇、2025 年 199 篇、2026 年 266 篇。
NeurIPS 2026 有多少篇信息抽取论文？
NeurIPS 2026 有 96 篇信息抽取论文，上一届是 80 篇。
ICLR 2026 有多少篇信息抽取论文？
ICLR 2026 有 63 篇信息抽取论文，上一届是 50 篇。
ICML 2026 有多少篇信息抽取论文？
ICML 2026 有 74 篇信息抽取论文，上一届是 46 篇。
CVPR 2026 有多少篇信息抽取论文？
CVPR 2026 有 33 篇信息抽取论文，上一届是 23 篇。
哪个会议的信息抽取论文最多？
NeurIPS，2023–2026 年共 287 篇。

「自然语言」下的其他主题