A multi-agent question generation pipeline produces long-context English and Arabic QA pairs (AraEngLongBench), and top LVLMs score below 50% on the resulting benchmark.
Docvqa: A dataset for vqa on document images,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Multi-Agent Interactive Question Generation Framework for Long Document Understanding
A multi-agent question generation pipeline produces long-context English and Arabic QA pairs (AraEngLongBench), and top LVLMs score below 50% on the resulting benchmark.