Information Extraction papers, 2023–2026

Key findings

• Information Extraction went from 143 papers in 2023 to 266 in 2026, roughly 1.9x in three years.
• NeurIPS publishes the most Information Extraction work: 287 papers from 2023 to 2026, 36% of the four-venue total.
• The fastest-growing overlap is with Diffusion Models: papers tagged with both rose from 2 in 2023 to 28 in 2026.
• Among the 5 topics under Natural Language, it ranks #3 by 2026 paper count; the fastest grower in the group, Retrieval-Augmented Generation, is up 5.4x versus 1.9x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Information Extraction papers

175 papers, page 2 of 4

51. ICLR 2026SIGMark: Scalable In-Generation Watermark with Blind Extraction for Video Diffusion
52. ICLR 2026SPICE: Submodular Penalized Information–Conflict Selection for Efficient Large Language Model Training
53. ICLR 2026The Spacetime of Diffusion Models: An Information Geometry Perspective
54. ICLR 2026The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss
55. ICLR 2026The Value of Information in Human-AI Decision-making
56. ICLR 2026There Was Never a Bottleneck in Concept Bottleneck Models
57. ICLR 2026To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
58. ICLR 2026Toward Principled Flexible Scaling for Self-Gated Neural Activation
59. ICLR 2026Towards Strategic Persuasion with Language Models
60. ICLR 2026Uncovering Semantic Selectivity of Latent Groups in Higher Visual Cortex with Mutual Information-Guided Diffusion
61. ICLR 2026Using maximal information auxiliary variables to improve synthetic data generation based on TabPFN foundation models
62. ICLR 2026What matters for Representation Alignment: Global Information or Spatial Structure?
63. ICLR 2026Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information
64. ICLR 2025A Benchmark for Semantic Sensitive Information in LLMs Outputs
65. ICLR 2025ACES: Automatic Cohort Extraction System for Event-Stream Datasets
66. ICLR 2025Active Learning for Continual Learning: Keeping the Past Alive in the Present
67. ICLR 2025ADAM: An Embodied Causal Agent in Open-World Environments
68. ICLR 2025AI2TALE: An Innovative Information Theory-based Approach for Learning to Localize Phishing Attacks
69. ICLR 2025AIMS.au: A Dataset for the Analysis of Modern Slavery Countermeasures in Corporate Statements
70. ICLR 2025An Information Criterion for Controlled Disentanglement of Multimodal Data
71. ICLR 2025Benchmarking LLMs' Judgments with No Gold Standard
72. ICLR 2025Bilinear MLPs enable weight-based mechanistic interpretability
73. ICLR 2025Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses
74. ICLR 2025Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
75. ICLR 2025Calibrating LLMs with Information-Theoretic Evidential Deep Learning
76. ICLR 2025Causal Information Prioritization for Efficient Reinforcement Learning
77. ICLR 2025Connectome Mapping: Shape-Memory Network via Interpretation of Contextual Semantic Information
78. ICLR 2025Data Pruning by Information Maximization
79. ICLR 2025Decision Information Meets Large Language Models: The Future of Explainable Operations Research
80. ICLR 2025Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning
81. ICLR 2025Dynamic Neural Fortresses: An Adaptive Shield for Model Extraction Defense
82. ICLR 2025Efficient Online Pruning and Abstraction for Imperfect Information Extensive-Form Games
83. ICLR 2025Exact Community Recovery under Side Information: Optimality of Spectral Algorithms
84. ICLR 2025Fast and Slow Streams for Online Time Series Forecasting Without Information Leakage
85. ICLR 2025Flow-based Variational Mutual Information: Fast and Flexible Approximations
86. ICLR 2025Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
87. ICLR 2025Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis
88. ICLR 2025Going Beyond Feature Similarity: Effective Dataset distillation based on Class-aware Conditional Mutual Information
89. ICLR 2025How many samples are needed to train a deep neural network?
90. ICLR 2025How Much is Unseen Depends Chiefly on Information About the Seen
91. ICLR 2025Inner Information Analysis Algorithm for Deep Neural Network based on Community
92. ICLR 2025Iterative Substructure Extraction for Molecular Relational Learning with Interactive Graph Information Bottleneck
93. ICLR 2025Laplace Sample Information: Data Informativeness Through a Bayesian Lens
94. ICLR 2025Learning Robust Representations with Long-Term Information for Generalization in Visual Reinforcement Learning
95. ICLR 2025Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD
96. ICLR 2025MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization
97. ICLR 2025Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
98. ICLR 2025Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization
99. ICLR 2025On Bits and Bandits: Quantifying the Regret-Information Trade-off
100. ICLR 2025On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking Functions

FAQ

How many Information Extraction papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

798 in total: 143 in 2023, 190 in 2024, 199 in 2025, 266 in 2026.

How many Information Extraction papers are at NeurIPS 2026?

NeurIPS 2026 has 96 Information Extraction papers, versus 80 the year before.

How many Information Extraction papers are at ICLR 2026?

ICLR 2026 has 63 Information Extraction papers, versus 50 the year before.

How many Information Extraction papers are at ICML 2026?

ICML 2026 has 74 Information Extraction papers, versus 46 the year before.

How many Information Extraction papers are at CVPR 2026?

CVPR 2026 has 33 Information Extraction papers, versus 23 the year before.

Which conference publishes the most Information Extraction papers?

NeurIPS, with 287 papers from 2023 to 2026.