信息抽取论文趋势 2023–2026

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。

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 190 篇，第 2 / 4 页

51. ICLR 2024Perceptual Scales Predicted by Fisher Information Metrics
52. ICLR 2024PRIME: Prioritizing Interpretability in Failure Mode Extraction
53. ICLR 2024Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction
54. ICLR 2024Rethinking Information-theoretic Generalization: Loss Entropy Induced PAC Bounds
55. ICLR 2024Separate and Diffuse: Using a Pretrained Diffusion Model for Better Source Separation
56. ICLR 2024Separating common from salient patterns with Contrastive Representation Learning
57. ICLR 2024Teach LLMs to Phish: Stealing Private Information from Language Models
58. ICLR 2024Towards Codable Watermarking for Injecting Multi-Bits Information to LLMs
59. ICML 2024Accurate LoRA-Finetuning Quantization of LLMs via Information Retention
60. ICML 2024An Information Theoretic Approach to Interaction-Grounded Learning
61. ICML 2024An Information-Theoretic Analysis of In-Context Learning
62. ICML 2024Assessing Large Language Models on Climate Information
63. ICML 2024Bidirectional Reciprocative Information Communication for Few-Shot Semantic Segmentation
64. ICML 2024Can Gaussian Sketching Converge Faster on a Preconditioned Landscape?
65. ICML 2024Causally Motivated Personalized Federated Invariant Learning with Shortcut-Averse Information-Theoretic Regularization
66. ICML 2024CLIPZyme: Reaction-Conditioned Virtual Screening of Enzymes
67. ICML 2024Decouple then Classify: A Dynamic Multi-view Labeling Strategy with Shared and Specific Information
68. ICML 2024Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks
69. ICML 2024Defense against Model Extraction Attack by Bayesian Active Watermarking
70. ICML 2024Discovering Environments with XRM
71. ICML 2024Error Feedback Can Accurately Compress Preconditioners
72. ICML 2024Gaussian Processes on Cellular Complexes
73. ICML 2024Highway Value Iteration Networks
74. ICML 2024How to Leverage Diverse Demonstrations in Offline Imitation Learning
75. ICML 2024Improving Computational Complexity in Statistical Models with Local Curvature Information
76. ICML 2024Incorporating Information into Shapley Values: Reweighting via a Maximum Entropy Approach
77. ICML 2024Inferring Change Points in High-Dimensional Linear Regression via Approximate Message Passing
78. ICML 2024InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization
79. ICML 2024Information Flow in Self-Supervised Learning
80. ICML 2024Information-Directed Pessimism for Offline Reinforcement Learning
81. ICML 2024Interpreting Equivariant Representations
82. ICML 2024Knowledge Graphs Can be Learned with Just Intersection Features
83. ICML 2024Latent Logic Tree Extraction for Event Sequence Explanation from LLMs
84. ICML 2024Learning High-Order Relationships of Brain Regions
85. ICML 2024Learning to Predict Mutational Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning
86. ICML 2024Leveraging (Biased) Information: Multi-armed Bandits with Offline Data
87. ICML 2024Localizing Task Information for Improved Model Merging and Compression
88. ICML 2024MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspective
89. ICML 2024Matrix Information Theory for Self-Supervised Learning
90. ICML 2024Mitigating Label Noise on Graphs via Topological Sample Selection
91. ICML 2024No Free Prune: Information-Theoretic Barriers to Pruning at Initialization
92. ICML 2024Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation
93. ICML 2024Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs
94. ICML 2024Performance Bounds for Active Binary Testing with Information Maximization
95. ICML 2024Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
96. ICML 2024Pi-DUAL: Using privileged information to distinguish clean from noisy labels
97. ICML 2024Prospective Side Information for Latent MDPs
98. ICML 2024Reinforcement Learning from Reachability Specifications: PAC Guarantees with Expected Conditional Distance
99. ICML 2024Repeat After Me: Transformers are Better than State Space Models at Copying
100. ICML 2024Rethinking Guidance Information to Utilize Unlabeled Samples: A Label Encoding Perspective

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。