AI RESEARCH
Evaluating Hallucinations in Audio-Visual Multimodal LLMs with Spoken Queries under Diverse Acoustic Conditions
arXiv CS.AI
•
ArXi:2510.08581v2 Announce Type: replace-cross Hallucinations in multimodal models have been extensively studied using benchmarks that probe reliability in image-text query settings. However, the effect of spoken queries on multimodal hallucinations remains largely unexplored, despite the growing role of voice interfaces. In this paper, we