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
- 信息抽取论文从 2023 年的 143 篇增长到 2026 年的 266 篇，三年间扩大到约 1.9 倍。
- NeurIPS 是发信息抽取论文最多的会议，2023–2026 年共 287 篇，占四个会议总量的 36%。
- 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 2 篇增至 2026 年的 28 篇。
- 在「自然语言」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的检索增强生成是 5.4 倍，信息抽取是 1.9 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 44 | 26 | 46 | 27 | 143 |
| 2024 | 67 | 36 | 65 | 22 | 190 |
| 2025 | 80 | 50 | 46 | 23 | 199 |
| 2026 | 96 | 63 | 74 | 33 | 266 |
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 2026$\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
- ICML 2026AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
- ICLR 2026An Information-Theoretic Parameter-Free Bayesian Framework for Probing Labeled Dependency Trees from Attention Score
- CVPR 2026ActiveGrasp Information-Guided Active Grasping with Calibrated Energy-based Model
- NeurIPS 2025A Pre-training Framework for Relational Data with Information-theoretic Principles
- ICML 2025A Peer-review Look on Multi-modal Clustering: An Information Bottleneck Realization Method
- ICLR 2025ADAM: An Embodied Causal Agent in Open-World Environments
- CVPR 2025A Focused Human Body Model for Accurate Anthropometric Measurements Extraction
- NeurIPS 2024TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools
- ICML 2024An Information-Theoretic Analysis of In-Context Learning
- ICLR 2024Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information
- CVPR 2024Differentiable Information Bottleneck for Deterministic Multi-view Clustering
- NeurIPS 2023A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspective
- ICML 2023Abstracting Imperfect Information Away from Two-Player Zero-Sum Games
- ICLR 2023A VAE for Transformers with Nonparametric Variational Information Bottleneck
- CVPR 2023"Seeing" Electric Network Frequency From Events
- NeurIPS 2026An Information-theoretic Framework for Auditing Unfairness in Training Data
- ICML 2026GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation
- ICLR 2026Calibrated Information Bottleneck for Trusted Multi-modal Clustering
- CVPR 2026Beyond Whats Shared Recovering Lost Unique Information from Intermediate Layers
全部信息抽取论文
共 798 篇，第 8 / 16 页
- ICML 2025De-mark: Watermark Removal in Large Language Models
- ICML 2025DeepCrossAttention: Supercharging Transformer Residual Connections
- ICML 2025Disentangling and Integrating Relational and Sensory Information in Transformer Architectures
- ICML 2025DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning
- ICML 2025Efficiently Access Diffusion Fisher: Within the Outer Product Span Space
- ICML 2025Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence
- ICML 2025Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective
- ICML 2025FIC-TSC: Learning Time Series Classification with Fisher Information Constraint
- ICML 2025Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator
- ICML 2025FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
- ICML 2025Fragments to Facts: Partial-Information Fragment Inference from LLMs
- ICML 2025Functional Alignment Can Mislead: Examining Model Stitching
- ICML 2025Generalization in Federated Learning: A Conditional Mutual Information Framework
- ICML 2025Graph4MM: Weaving Multimodal Learning with Structural Information
- ICML 2025Information Bottleneck-guided MLPs for Robust Spatial-temporal Forecasting
- ICML 2025Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback
- ICML 2025Learning Likelihood-Free Reference Priors
- ICML 2025Learning Optimal Multimodal Information Bottleneck Representations
- ICML 2025Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection
- ICML 2025NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations
- ICML 2025Noise-Guided Predicate Representation Extraction and Diffusion-Enhanced Discretization for Scene Graph Generation
- ICML 2025On the Importance of Gaussianizing Representations
- ICML 2025Online Curvature-Aware Replay: Leveraging $\mathbf{2^{nd}}$ Order Information for Online Continual Learning
- ICML 2025Optimal Information Retention for Time-Series Explanations
- ICML 2025PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning
- ICML 2025Pointwise Information Measures as Confidence Estimators in Deep Neural Networks: A Comparative Study
- ICML 2025Position: Language model developers should report train-test overlap
- ICML 2025ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputation
- ICML 2025Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks
- ICML 2025ROME is Forged in Adversity: Robust Distilled Datasets via Information Bottleneck
- ICML 2025Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation
- ICML 2025Sharp Optimality of Simple, Plug-in Estimation of the Fisher Information of a Smoothed Density
- ICML 2025Super Deep Contrastive Information Bottleneck for Multi-modal Clustering
- ICML 2025The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability
- ICML 2025ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
- NeurIPS 2025A Pre-training Framework for Relational Data with Information-theoretic Principles
- NeurIPS 2025A Semantic Parsing Framework for End-to-End Time Normalization
- NeurIPS 2025Balanced Active Inference
- NeurIPS 2025ChemX: A Collection of Chemistry Datasets for Benchmarking Automated Information Extraction
- NeurIPS 2025ClinBench: A Standardized Multi-Domain Framework for Evaluating Large Language Models in Clinical Information Extraction
- NeurIPS 2025Collective Bargaining in the Information Economy Can Address AI-Driven Power Concentration
- NeurIPS 2025Conformal Information Pursuit for Interactively Guiding Large Language Models
- NeurIPS 2025Connecting Jensen–Shannon and Kullback–Leibler Divergences: A New Bound for Representation Learning
- NeurIPS 2025CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision
- NeurIPS 2025CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning
- NeurIPS 2025DataSIR: A Benchmark Dataset for Sensitive Information Recognition
- NeurIPS 2025Decomposing Interventional Causality into Synergistic, Redundant, and Unique Components
- NeurIPS 2025Decomposing stimulus-specific sensory neural information via diffusion models
- NeurIPS 2025Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
- NeurIPS 2025Efficient Kernelized Learning in Polyhedral Games beyond Full Information: From Colonel Blotto to Congestion Games
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"}
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。