Problem
Research questions and friction points this paper is trying to address.
Cross-Lingual Degradation
Multilingual Medical VQA
Vision-Language Models
Analyzing and Mitigating Cross-Lingual Degradation in Multilingual Medical VQA
🤖 AI Summary
本文针对多语言医学VQA中的跨语言性能下降问题，通过构建多语言基准并提出MedVL-XLRepE方法来缓解非英语语言的性能退化。
📝 Abstract
Medical visual question answering (VQA) is a crucial task in clinical AI, yet its evaluation has so far centered almost exclusively on English, limiting its relevance to linguistically diverse patients and clinicians. Recent multilingual medical VQA benchmarks show that large vision-language models (LVLMs) degrade in non-English languages, but lack a fine-grained analysis of how cross-lingual variation affects the distinct capabilities that medical VQA requires. To this end, we construct a multilingual medical VQA benchmark over eight languages, organized into four representative scenarios that isolate the core capabilities medical VQA requires. Evaluating five open- and closed-source LVLMs, we find that cross-lingual degradation is not uniform but highly scenario-dependent. We therefore propose MedVL-XLRepE, a training-free scenario-aware representation engineering method, leveraging LVLMs' superior English medical VQA capability to steer non-English representations toward their English counterparts at inference time. Across three LVLMs and eight languages, MedVL-XLRepE consistently mitigates cross-lingual degradation, with gains of up to 6.33\%.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multilingual Medical VQA
Cross-lingual Degradation
Scenario-aware Representation Engineering
MedVL-XLRepE
🔎 Similar Papers
No similar papers found.
