EaGERS uses a vision language model's own explanation to mask a document image to relevant grid regions, then re-asks the question, improving DocVQA accuracy while grounding answers spatially.
In: European Conference on Computer Vision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Spatially Grounded Explanations in Vision Language Models for Document Visual Question Answering
EaGERS uses a vision language model's own explanation to mask a document image to relevant grid regions, then re-asks the question, improving DocVQA accuracy while grounding answers spatially.