作者位次 #3/9ACL 2026Findings· Findings of ACL
S imple OCR : Rendering Visual Questions to Teach MLLM s to Read
Yibo Peng · Peng Xia · Ding Zhong · Kaide Zeng · Siwei Han · Yiyang Zhou · Jiaqi Liu · Ruiyi Zhang · Huaxiu Yao
摘要
Despite the rapid advancements in Multimodal Large Language Models (MLLMs), a critical question regarding their visual grounding mechanism remains unanswered: do these models genuinely read text embedded in images, or do they merely rely on parametric shortcuts in the text prompt? In this work, w...