A new perturbation test shows that medical vision-language models rely more on clinical text than on images, with calibration errors growing when text conflicts with the image.
Faithful Multimodal Explanation for Visual Question Answering
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
AI systems' ability to explain their reasoning is critical to their utility and trustworthiness. Deep neural networks have enabled significant progress on many challenging problems such as visual question answering (VQA). However, most of them are opaque black boxes with limited explanatory capability. This paper presents a novel approach to developing a high-performing VQA system that can elucidate its answers with integrated textual and visual explanations that faithfully reflect important aspects of its underlying reasoning while capturing the style of comprehensible human explanations. Extensive experimental evaluation demonstrates the advantages of this approach compared to competing methods with both automatic evaluation metrics and human evaluation metrics.
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Risk of Misleading Reports: Diagnosing Textual Biases in Multimodal Clinical AI
A new perturbation test shows that medical vision-language models rely more on clinical text than on images, with calibration errors growing when text conflicts with the image.