作者位次 #2/7ACL 2026Findings· Findings of ACL
MTMCS -Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues
Zheyuan Liu · Dongwhi Kim · Yixin Wan · Xiangchi Yuan · Zhaoxuan Tan · Fengran Mo · Meng Jiang
摘要
Multimodal large language models (MLLMs) are increasingly deployed as assistants that interact through text and images, making it crucial to evaluate contextual safety when risk depends on both the visual scene and the evolving dialogue. Existing contextual safety benchmarks are mostly single-tur...