AI RESEARCH
Separate First, Fuse Later: Mitigating Cross-Modal Interference in Audio-Visual LLMs Reasoning with Modality-Specific Chain-of-Thought
arXiv CS.AI
•
ArXi:2605.09906v1 Announce Type: new Audio and vision provide complementary evidence for audio-visual question answering, yet current audio-visual large language models may suffer from cross-modal interference: information from one modality misguides the interpretation of another, thereby inducing hallucinations. We attribute this issue to uncontrolled cross-modal interactions during intermediate reasoning. To mitigate this, we propose Separate First, Fuse Later (SFFL), an audio-visual reasoning framework designed to reduce cross-modal interference.