作者位次 #2/5ACL 2026Findings· Findings of ACL
Empowering Reliable Visual-Centric Instruction Following in MLLM s
Weilei He · Feng Ju · Zhiyuan Fan · Rui Min · Minhao Cheng
摘要
Evaluating the instruction-following (IF) capabilities of Multimodal Large Language Models (MLLMs) is essential for rigorously assessing how faithfully model outputs adhere to user-specified intentions. Nevertheless, existing benchmarks for evaluating MLLMs’ instruction-following capability prima...