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 287 篇，第 3 / 6 页

101. NeurIPS 2025ClinBench: A Standardized Multi-Domain Framework for Evaluating Large Language Models in Clinical Information Extraction
102. NeurIPS 2025Collective Bargaining in the Information Economy Can Address AI-Driven Power Concentration
103. NeurIPS 2025Conformal Information Pursuit for Interactively Guiding Large Language Models
104. NeurIPS 2025Connecting Jensen–Shannon and Kullback–Leibler Divergences: A New Bound for Representation Learning
105. NeurIPS 2025CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision
106. NeurIPS 2025CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning
107. NeurIPS 2025DataSIR: A Benchmark Dataset for Sensitive Information Recognition
108. NeurIPS 2025Decomposing Interventional Causality into Synergistic, Redundant, and Unique Components
109. NeurIPS 2025Decomposing stimulus-specific sensory neural information via diffusion models
110. NeurIPS 2025Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
111. NeurIPS 2025Efficient Kernelized Learning in Polyhedral Games beyond Full Information: From Colonel Blotto to Congestion Games
112. NeurIPS 2025Enhancing Privacy in Multimodal Federated Learning with Information Theory
113. NeurIPS 2025Evolution of Information in Interactive Decision Making: A Case Study for Multi-Armed Bandits
114. NeurIPS 2025Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training
115. NeurIPS 2025Fantastic Features and Where to Find Them: A Probing Method to combine Features from Multiple Foundation Models
116. NeurIPS 2025FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning
117. NeurIPS 2025Feedback-Aware MCTS for Goal-Oriented Information Seeking
118. NeurIPS 2025FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
119. NeurIPS 2025FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction
120. NeurIPS 2025From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks
121. NeurIPS 2025From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD
122. NeurIPS 2025Glocal Information Bottleneck for Time Series Imputation
123. NeurIPS 2025Graph–Smoothed Bayesian Black-Box Shift Estimator and Its Information Geometry
124. NeurIPS 2025Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs
125. NeurIPS 2025H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition
126. NeurIPS 2025HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks
127. NeurIPS 2025Hierarchical Information Aggregation for Incomplete Multimodal Alzheimer's Disease Diagnosis
128. NeurIPS 2025High Resolution UDF Meshing via Iterative Networks
129. NeurIPS 2025HyperMixup: Hypergraph-Augmented with Higher-order Information Mixup
130. NeurIPS 2025IGD: Token Decisiveness Modeling via Information Gain in LLMs for Personalized Recommendation
131. NeurIPS 2025Improving Target Sound Extraction via Disentangled Codec Representations with Privileged Knowledge Distillation
132. NeurIPS 2025Improving the Straight-Through Estimator with Zeroth-Order Information
133. NeurIPS 2025InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions
134. NeurIPS 2025Information Theoretic Learning for Diffusion Models with Warm Start
135. NeurIPS 2025Information-Computation Tradeoffs for Noiseless Linear Regression with Oblivious Contamination
136. NeurIPS 2025Information-Driven Design of Imaging Systems
137. NeurIPS 2025Information-Theoretic Discrete Diffusion
138. NeurIPS 2025Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variables
139. NeurIPS 2025Information-Theoretic Reward Decomposition for Generalizable RLHF
140. NeurIPS 2025ItDPDM: Information-Theoretic Discrete Poisson Diffusion Model
141. NeurIPS 2025Learning to Generalize: An Information Perspective on Neural Processes
142. NeurIPS 2025Learning to price with resource constraints: from full information to machine-learned prices
143. NeurIPS 2025Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs
144. NeurIPS 2025Long-Tailed Recognition via Information-Preservable Two-Stage Learning
145. NeurIPS 2025Make Information Diffusion Explainable: LLM-based Causal Framework for Diffusion Prediction
146. NeurIPS 2025Median Selection with Noisy and Structural Information
147. NeurIPS 2025MI-TRQR: Mutual Information-Based Temporal Redundancy Quantification and Reduction for Energy-Efficient Spiking Neural Networks
148. NeurIPS 2025Missing Data Imputation by Reducing Mutual Information with Rectified Flows
149. NeurIPS 2025Multimodal Tabular Reasoning with Privileged Structured Information
150. NeurIPS 2025Neural Entropy

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。