DRAGON is a new benchmark with 11,664 annotated instances from six diagram QA datasets that requires models to localize visual evidence regions supporting their answers.
Err on the side of includingmore elements rather than fewer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DRAGON: A Benchmark for Evidence-Grounded Visual Reasoning over Diagrams
DRAGON is a new benchmark with 11,664 annotated instances from six diagram QA datasets that requires models to localize visual evidence regions supporting their answers.