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 266 篇，第 5 / 6 页
- NeurIPS 2026FMMI: Flow Matching Mutual Information Estimation
- NeurIPS 2026From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs
- NeurIPS 2026GISA: A Benchmark for General Information-Seeking Assistant
- NeurIPS 2026Harnessing Data Asymmetry in Manifold Learning
- NeurIPS 2026How Much Information is Needed for Accurate Kalman Filtering?
- NeurIPS 2026Identified-Set Geometry of Distributional Model Extraction under Top-K Censored API Access
- NeurIPS 2026Information bottleneck dynamics during learning across artificial and biological neural systems
- NeurIPS 2026Information Bottleneck-Guided Adaptive Hypergraph Transformer for Brain Disease Diagnosis
- NeurIPS 2026Information Discernment in Large Language Models
- NeurIPS 2026Information Loss and Disparate Effects in Network Embeddings
- NeurIPS 2026Information Parity for Code: The Scope of Transfer in Multilingual Code Models
- NeurIPS 2026Information Templates: A New Paradigm for Intelligent Active Feature Acquisition
- NeurIPS 2026Information-Geometric Forward Policy Training in GFlowNets
- NeurIPS 2026InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting
- NeurIPS 2026Intrinsic Information Theoretic Analysis of ReLU Nets
- NeurIPS 2026Large Language Model Selection with Limited Annotations
- NeurIPS 2026Learning Actionable Information Landscapes for Multimodal Active Sensing in Hawkmoths
- NeurIPS 2026Learning to Persuade a Biased Receiver
- NeurIPS 2026Learning to Read Out: Unembedding Dynamics in Language Model Pretraining
- NeurIPS 2026Learning to target with network interference
- NeurIPS 2026Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise
- NeurIPS 2026MatCurvs: Article Real-Coordinate Curve Extraction for Agent-Ready Materials Reasoning
- NeurIPS 2026Matrix-Free Natural Gradient via Stochastic Truncated Metrics
- NeurIPS 2026Mind the Gap: Information Disadvantage as a Learning Signal in Cooperative MARL
- NeurIPS 2026MIRA: Mutual Information guided calibration for Reliable Test-Time Adaptation
- NeurIPS 2026No Coin Left Behind: Maximizing Strategic Surplus Against No-Regret Dynamics
- NeurIPS 2026On Making $SE(2)$-Invariant Networks Optimal
- NeurIPS 2026On Minimizing Regret in Fixed-Confidence $\varepsilon$-Best Arm Identification
- NeurIPS 2026On Reparameterizing the Score Function
- NeurIPS 2026On the Impact of Side-Information in Bandit Learning: More is Not Always Merrier
- NeurIPS 2026On the Information Loss of Multi-Token Prediction: Origin and Solution
- NeurIPS 2026Opening the Black Box of Classifier-Free Guidance via Information Bottleneck
- NeurIPS 2026PAC Learning with Bandit Feedback: Sharp Sample Complexity in the Realizable Setting
- NeurIPS 2026PANDA: Prior-guided Attentional Dual-path Architecture
- NeurIPS 2026PatchScout: Thematic Web Data Collection via Information Foraging
- NeurIPS 2026Pathways of Visual Information Flow in Vision-Language Models
- NeurIPS 2026PepDDG: Peptide–Protein Binding ΔΔ𝐺 Prediction via Information Channel Decomposition
- NeurIPS 2026PLACE: Patch-Level Agnostic Concept Extraction
- NeurIPS 2026PRISM: Prior Relational Information for Self-supervised Modeling to Enhance Solubility OOD Generalization
- NeurIPS 2026Reading Positional Coupling in Transformers with Diffusion Scores
- NeurIPS 2026Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck
- NeurIPS 2026Refinement as a Service: Algorithmic Predictor Refinement
- NeurIPS 2026Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching
- NeurIPS 2026Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information
- NeurIPS 2026Robust Multi-view Clustering against Imperfect Information
- NeurIPS 2026SAME: Stability-Aware Embedding Extraction in Mixture-of-Experts Language Models
- NeurIPS 2026SBNO : Schrödinger Bridge Neural Operator for the Forward and Inverse Problems under Missing Information
- NeurIPS 2026Securing AI Agents with Information-Flow Control
- NeurIPS 2026Self-Distilled RLVR
- NeurIPS 2026Selling Information While Being an Interested Party
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。