REVIEW 2 cited by
Faithful Multimodal Explanation for Visual Question Answering
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 2 Pith papers
-
On Explaining Visual Captioning with Hybrid Markov Logic Networks
A hybrid Markov logic network selects training examples that plausibly biased a captioning model's output for a test image, and user studies rate those selections as interpretable.
-
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.
Discussion (0). Continue with ORCID to comment.