Skip to main navigation Skip to search Skip to main content

Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment Tuning

  • Aofei Chang
  • , Le Huang
  • , Alex James Boyd
  • , Parminder Bhatia
  • , Taha Kass-Hout
  • , Cao Xiao
  • , Fenglong Ma

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Medical Large Vision-Language Models (Med-LVLMs) often exhibit suboptimal attention distribution on visual inputs, leading to hallucinated or inaccurate outputs. Existing mitigation methods primarily rely on inference-time interventions, which are limited in attention adaptation or require additional supervision. To address this, we propose A3TUNE, a novel fine-tuning framework for Automatic Attention Alignment Tuning. A3TUNE leverages zero-shot weak labels from SAM, refines them into prompt-aware labels using BiomedCLIP, and then selectively modifies visually-critical attention heads to improve alignment while minimizing interference. Additionally, we introduce a A3MOE module, enabling adaptive parameter selection for attention tuning across diverse prompts and images. Extensive experiments on medical VQA and report generation benchmarks show that A3TUNE outperforms state-of-the-art baselines, achieving enhanced attention distributions and performance.

Original languageEnglish (US)
Title of host publicationLong Papers
EditorsWanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar
PublisherAssociation for Computational Linguistics (ACL)
Pages9357-9372
Number of pages16
ISBN (Electronic)9798891762510
DOIs
StatePublished - 2025
Event63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025 - Vienna, Austria
Duration: Jul 27 2025Aug 1 2025

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume1
ISSN (Print)0736-587X

Conference

Conference63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025
Country/TerritoryAustria
CityVienna
Period7/27/258/1/25

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Linguistics and Language
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment Tuning'. Together they form a unique fingerprint.

Cite this