Papers by Qiyuan Fan

1 papers
DocAssistant: Integrating Key-region Reading and Step-wise Reasoning for Robust Document Visual Question Answering (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing document understanding models focus on key information and generate answers straightforwardly . existing models ignore evidence from source documents and lack interpretability .
Approach: They propose a visual encoder that fuses text into visual encoded visual encodes . they use multimodal large language models as data generators and checkers to generate step-wise question-and-answer pairs for document images.
Outcome: The proposed model can answer step-wise questions without compromising the performance of the original model.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations