作者位次 #5/11ACL 2026Poster· Natural Language Processing
Probing Audio-Visual Reasoning in Multimodal Language Models through the Lens of Audio
Kaixiong Gong · Kaituo Feng · Bohao Li · Yibing Wang · Mofan Cheng · Shijia Yang · Jiaming Han · Benyou Wang · Yutong Bai · Zhuoran Yang · Xiangyu Yue
摘要
Recent multimodal large language models (MLLMs), such as GPT-4o, Gemini 1.5/2.5 Pro, and Reka Core, have advanced audio-visual reasoning capabilities, achieving strong performance in tasks like cross-modal understanding and generation. However, our DeafTest uncovers unanticipated failures: most o...