作者位次 #3/6ACL 2026Findings· Findings of ACL
Switching Heads and Softening Tokens: Turnkey Solutions to Visually Grounded Document QA
Ximing Wen · Wenbo Li · Sudipta Paul · Yashas Malur Saidutta · Kalpa Gunaratna · Srinivas Chappidi
摘要
Visually Grounded Document Question Answering often lacks robust, end-to-end solutions capable of handling complex, multi-answer queries without reliance on ad-hoc processing. In this work, we propose two turnkey LLM architectures to address this gap. We first introduce a single-head architecture...