SVHalluc: Benchmarking Speech-Vision Hallucination in Audio-Visual Large Language Models 文章

ArXiv CS.CV2026-06-03NEWSen作者: Chenshuang Zhang, Kyeong Seon Kim, Chengxin Liu, Tae-Hyun Oh

摘要

arXiv:2606.02642v1 Announce Type: cross Abstract: Despite the success of audio-visual large-language models (LLMs), they can produce plausible but ungrounded outputs, termed hallucination. Existing benchmarks focus on environmental sounds (e.g., dog barking) to indicate event occurrence. In contrast, human speech carries fundamentally different, rich semantics and temporal structures, yet it remains unexplored whether current models can accurately align speech content with corresponding visual signals. In this work, we show that speech content can induce hallucinations in audio-visual LLMs. To systematically study this, we introduce SVHalluc, the first comprehensive benchmark for evaluating speech-vision hallucination in audio-visual LLMs. Our benchmark diagnoses speech-vision hallucinations from two critical and complementary aspects: semantic and temporal.

相关事件

暂无数据

相关公司

暂无数据

相关人物

暂无数据

相关技术

暂无数据