Attention Head Analysis

Ask about this topic

Overview

The field investigates the roles, interactions, and stability of attention heads, including their contributions to induction, retrieval, reasoning, and multimodal tasks. Common approaches include head ablation and activation patching to test causal effects, alongside probes and spectral or geometric analyses to identify patterns and redundancies. These methods support both interpretability and practical goals such as pruning, bias analysis, and efficient inference across language, vision, and multimodal models. A central challenge is that attention patterns or probe scores do not by themselves establish a head’s causal role: effects can depend on the task, prompt, architecture, and controls used.

Latest papers

CardsList

82 papers16 papers in the last four weeks, up 45% on the four weeks before. 0.1% of all new papers.

  1. Causal Localization of Evidence Effects in Transformers

    Oct 27, 2026Jipeng Li, Pramod Khargonekar, Yanning ShenTransformer InterpretabilityAttention Head Analysis

  2. SVD-Attention: Efficiently Analyzing Attention Blocks in Transformers

    Oct 26, 2026Debopam Sanyal, Hongjie Chen, Riya Elizabeth Kuriyan +5Transformer AttentionAttention Head Analysis

    Georgia Institute of Technology · Dolby Laboratories

  3. Head Dimension Matters in Language Models for Long-Context Retrieval

    Oct 23, 2026Seiya Tokui, Shoichiro Yamaguchi, Sosuke KobayashiLong-Context RetrievalAttention Head Analysis

    Preferred Networks, Inc., Tokyo, Japan

  4. One Head Away from Language Confusion: Single Attention Heads Across Model Families

    Oct 18, 2026Jiwon Jeong, Anjelo Jann Laroza, Chaewoon Yoon +4Multilingual Language ModelsAttention Head Analysis

    Lotte Innovate · Mapúa University · University of Wisconsin–Madison +4

  5. Spurious Attention Heads in Vision Transformers: Mechanistic Identification of Annotation-Driven Bias in Medical Chest X-Ray Analysis

    Oct 15, 2026Joshua Muhumuza, Cornelius KalenziVision TransformerAttention Head Analysis

    Makerere University

  6. Can Capability Enhancement be Localized?

    Oct 15, 2026Anh Tuan Nguyen, Anna Bair, Zico KolterAttention Head AnalysisMulti-Head Attention

    Carnegie Mellon University

  7. Exploring Attention Sinks in Text-to-Image Transformers from Diffusion and Autoregressive Models

    Oct 9, 2026Binglei Li, Mengping Yang, Zhiyu Tan +3Attention SinksTransformer Interpretability

    Fudan University · Shanghai Innovation Institute · Shanghai Academy of AI for Science

  8. What Do Visual-Head Discovery Scores Actually Find? Attention Source, Necessity, and Random-Control Pitfalls in Vision-Language Models

    Oct 9, 2026Md Abdul Kadir, Daniel SonntagAttention Head AnalysisVision-Language Models

    German Research Center for Artificial Intelligence (DFKI) Saarbrücken, Germany · Oldenburg University Oldenburg, Germany

  9. Finding the Heads and the Neurons Responsible for Network Information Retrieval in Language Models

    Oct 6, 2026Md Abdul Kadir, Md Mohasin Hossain, Daniel SonntagAttention Head AnalysisLLM Interpretability

    University of Oldenburg, Oldenburg, Germany · German Research Center for Artificial Intelligence · Saarland University, Saarbrucken, Germany

  10. Spectral Geometry of Attention: From Information Routing to Uncertainty

    Oct 5, 2026Giulio Viganò, Simone Melzi, Maks OvsjanikovAttention Head AnalysisAttention Sinks

    University of Milano-Bicocca Milan, Italy · Ecole Polytechnique · LIX, Ecole Polytechnique IP Paris

  11. Emergent Structure in the Marginal Attention Space of Language Models

    Oct 2, 2026Valentino Maiorca, Walter Nelson, Francesco LocatelloAttention MechanismsAttention Head Analysis

    Institute of Science and Technology Austria (ISTA)

  12. Attention Function as an Intrinsic Inductive Bias: How Models' Behavior Diverges in Novel Contexts

    Sep 30, 2026Dong Gyun Kang, Megha Thukral, Kwangsoo KimAttention Head AnalysisOOD Generalization

    College of Computing, Georgia Institute of Technology · Department of Transdisciplinary Medicine, Seoul National University Hospital

  13. When Do Attention-Head Ablations Support Causal Claims? Projection-Level Confounds, Floor Effects, and Matched Controls

    Sep 30, 2026Juli HuangAttention Head AnalysisCausal Interventions in Language Models

    Stanford University

  14. Which Attention Heads are like the Human Head? Not the Ones that Compute

    Sep 29, 2026Christopher Pinier, Gustaw Opiełka, Hannes Rosenbusch +3Attention Head AnalysisCross-Modal Alignment

    Psychological Methods, University of Amsterdam, Amsterdam, The Netherlands · Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA

  15. When Can Prefixes Compile LoRA? Exact Resource-Capped Tests for Frozen Attention

    Sep 29, 2026Joyanta Jyoti Mondal, Ibne Farabi ShihabPrefix TuningLow-Rank Adaptation

    Department of Computer and Information Sciences, University of Delaware, USA · Department of Computer Science, Iowa State University, USA

  16. How Language Models Differ in Redistributing Attention-Head Activity Under Serial Demand

    Sep 28, 2026Johnny Jingze Li, Abdulla Kuleib, Kalyan Basu +1Attention Head AnalysisLLM Interpretability

    Carnegie Mellon University · University of California, San Diego · Qualtrics LLC

  17. A mechanistic study of language model introspection

    Sep 28, 2026Jiahong Zou, Xiangkun Sun, Lingkai Kong +1Attention Head AnalysisLLM Interpretability

    Shandong University · Tsinghua University · Northeastern University +1

  18. When Can Attention Heads Be Statically Defined?

    Sep 28, 2026Weixian Waylon Li, Yintao Tai, Marcio Fonseca +1Attention Head AnalysisEfficient Attention

    University of Edinburgh, United Kingdom · Chamber of Deputies, Brazil

  19. Rethinking Contextualization by Reinterpreting Attention Head Channels

    Sep 27, 2026Hakaze Cho, Haolin Yang, Zhun Sun +3Attention Head AnalysisRepresentation Geometry in Language Models

    RIKEN · Tohoku University · New York University +2

  20. Scaling Attention Head Analysis via Gradient-Based Attribution in Context-Aware Machine Translation

    Sep 23, 2026Paweł Mąka, Yusuf Can Semerci, Jan Scholtes +1Gradient-Based AttributionAttention Head Analysis

    Department of Advanced Computing Sciences Maastricht University

  21. Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer

    Sep 20, 2026David LitmanTransformer InterpretabilityAttention Head Analysis

    Computational Neurobiology Laboratory, Salk Institute

  22. Global Ranks Survive, Selected Heads Shift: BOS-Sink Topology under 4-bit Weight-Only Quantization

    Sep 20, 2026Kuanlin Chen, Chen-Wei Kuo, Cheng-En OuAttention Head Analysis4-Bit Quantization

    Independent Researcher Taoyuan, Taiwan · National Tsing Hua University Hsinchu, Taiwan

  23. On attention heads and bilinear forms

    Sep 19, 2026Andrew O'DeskyAttention Head AnalysisAttention Mechanisms

  24. Attention Mean Fields Predict Average Representation Dynamics and Reveal Context-Specific Computation

    Sep 14, 2026Micah Adler, John W. Byers, Mark CrovellaAttention Head AnalysisIn-Context Learning

    Department of Computer Science, Boston University · Faculty of Computing & Data Sciences, Boston University

  25. Temporal-Attention Head Specialization During Video Diffusion Training

    Sep 14, 2026Taewoo Ha, Shafayat Mowla Anik, Dae Yeol Lee +2Video Diffusion ModelsAttention Head Analysis

    Independent Researcher · University of Colorado - Colorado Springs · Dolby Laboratories +1

  26. Inherited Heads: Audio language models track speakers with their text backbone's attention, and an attention-mass ranking retrieves a different set

    Sep 12, 2026Bojro DasAudio-Language ModelsAttention Head Analysis

    Cornell University

  27. Influence Score and Transformers interpretability: Measure of the Effective Impact of Attention Heads at inference time

    Sep 4, 2026Lisa Bouger, Yannick Teglia, Philippe Loubet MoundiTransformer InterpretabilityAttention Head Analysis

    Thales CDI, France · Inria Paris, France · Sorbonne Université, France

  28. Scaled Idempotence in Transformer Attention: Paired OV Geometry and Shared-Value Algebras

    Sep 1, 2026Jiming Feng, Junliang LiAttention Head AnalysisTransformer Attention

    College of Computer Science, Beijing University of Technology Beijing, China · School of Mathematics, Statistics and Mechanics, Beijing University of Technology Beijing, China

  29. Inherent Trade-offs when Enforcing Correct Data Symmetries in Multi-head Self-attention

    Aug 31, 2026Tīkun Ông, Georg BökmanAttention Head AnalysisEquivariant Neural Networks

  30. Importance Scoring of Transformer Attention Heads in Learning Tabular Data

    Aug 27, 2026Ahmad Jad Allah, Kazi F. Akhter, Md. Kamrozzaman Bhuiyan +1Attention Head AnalysisTransformer Attention

    Department of Computer Science Tennessee State University Nashville, TN, USA · Enosis Solutions Dhaka, Bangladesh · Department of Computer Science North Carolina Agricultural and Technical University Greensboro, NC, USA