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 266 篇，第 3 / 6 页

101. ICML 2026AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
102. ICML 2026Attention Implements the Fisher Geometry of Exponential Families
103. ICML 2026Beyond Accuracy and Complexity: The Effective Information Criterion for Structurally Stable Symbolic Regression
104. ICML 2026Bits That Count: Quantifying and Predicting Capabilities of Language Models
105. ICML 2026Closing the Expression Gap in LLM Instructions via Socratic Questioning
106. ICML 2026Coupled Training with Privileged Information and Unlabeled Data
107. ICML 2026Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
108. ICML 2026Credible Information Subset Decomposition: An End-to-End Multi-fidelity Learning Model by Modeling Label Information
109. ICML 2026CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks
110. ICML 2026DataGuard: A Non-intrusive Dataset Auditing Framework via Differential Information Forensics
111. ICML 2026Do Activation Verbalization Methods Convey Privileged Information?
112. ICML 2026Eigenvectors of Experts are Training-free Non-collapsing Routers
113. ICML 2026Entropy-informed Decoding: Adaptive Information-Driven Branching
114. ICML 2026Envy-Free Allocation of Indivisible Goods via Noisy Queries
115. ICML 2026Estimating the Empowerment of Language Model Agents
116. ICML 2026FedFit: Federated Dynamic Sparse Training via Fisher Information scoring
117. ICML 2026Few-Shot Design Optimization by Exploiting Auxiliary Information
118. ICML 2026Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information Gain
119. ICML 2026Forgetting Whenever You Want: A Decentralized Continual Learning Framework with On-Demand Unlearning
120. ICML 2026GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation
121. ICML 2026GEM-FI: Gated Evidential Mixtures with Fisher Modulation
122. ICML 2026HIAL: Towards Semantics-Aware Hypergraph Active Learning via Dual-Perspective Information Maximization
123. ICML 2026IBMA: Information Bottleneck-Based Multimodal Alignment
124. ICML 2026InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization
125. ICML 2026InfoGlobe: Local-and-Global Information-Preserving Statistical Manifold Learning for Single-Cell Transcriptomics
126. ICML 2026Information dynamics and Memory in Neural Networks through Fisher Information Diffusion
127. ICML 2026Information Flow Reveals When to Trust Language Models
128. ICML 2026Information Geometry Loss for Time Series Forecasting
129. ICML 2026Information-Geometric Adaptive Sampling for Graph Diffusion
130. ICML 2026Information-Theoretic Generalization Bounds for VAEs: A Role of Encoder and Latent Variable
131. ICML 2026Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access
132. ICML 2026KUMA: A Novel Framework with Koopman Separation and Efficient Multilevel Extraction in Time Series Forecasting
133. ICML 2026Label-Guided Representation Learning for Incomplete Multi-View Multi-Label Classification
134. ICML 2026Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens
135. ICML 2026Learn from A Rationalist: Distilling Intermediate Interpretable Rationales
136. ICML 2026Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization
137. ICML 2026Local Redundancy: An Information-Theoretic Measure of Plasticity from Synthetic Memorization
138. ICML 2026Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data
139. ICML 2026Networked Information Aggregation for Binary Classification
140. ICML 2026Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attacks
141. ICML 2026On the Separability of Information in Diffusion Models
142. ICML 2026Online Fair Division with Additional Information
143. ICML 2026ParalESN: Enabling parallel information processing in Reservoir Computing
144. ICML 2026Partitioning for Intrinsic Model Inversion Resistance in Collaborative Inference
145. ICML 2026Predictable Compression Failures: Order Sensitivity and Information Budgeting for Evidence-Grounded Binary Adjudication
146. ICML 2026Probing the Knowledge Boundary: An Interactive Agentic Framework for Deep Knowledge Extraction
147. ICML 2026Provable Accuracy Collapse of Embedding-Based Representations under Dimensionality Mismatch
148. ICML 2026Provably Learning Attention with Queries
149. ICML 2026Provably Protecting Fine-Tuned LLMs from Training Data Extraction while Preserving Utility
150. ICML 2026Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations

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。