作者位次 #3/6ACL 2026Poster· Natural Language Processing
H allu A udio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models
Feiyu Zhao · Yiming Chen · Wenhuan Lu · Daipeng Zhang · Xianghu Yue · Jianguo Wei
摘要
Large Audio-Language Models (LALMs) have recently achieved strong performance across various audio-centric tasks. However, hallucination, where models generate responses that are semantically incorrect or acoustically unsupported, remains largely underexplored in the audio domain. Existing halluc...