Extending the linguistic theory of Questions Under Discussion to multimodal scientific figures produces the MQUD dataset of author-annotated questions and improves VLM generation of content-specific multimodal questions.
What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian- Noise-free Text-Image Corruption and Evaluation.arXiv preprint, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multimodal QUD: Inquisitive Questions from Scientific Figures
Extending the linguistic theory of Questions Under Discussion to multimodal scientific figures produces the MQUD dataset of author-annotated questions and improves VLM generation of content-specific multimodal questions.