作者位次 #5/7ACL 2026Findings· Findings of ACL
Pardon? Evaluating Conversational Repair in Large Audio-Language Models
Shuanghong Huang · Jinlei Xu · Youchao Zhou · Yanghao Zhou · Xuan Zhao · Chong Feng · Wenxuan Zhang
摘要
Large Audio-Language Models (LALMs) have demonstrated strong performance in spoken question answering (QA), with existing evaluations primarily focusing on answer accuracy and robustness to acoustic perturbations. However, such evaluations implicitly assume that spoken inputs remain semantically...