Do Audio-Visual Large Language Models Really See and Hear?

Computer Science > Artificial Intelligence [Submitted on 3 Apr 2026] Do Audio-Visual Large Language Models Really See and Hear? Ramaneswaran Selvakumar, Kaousheik Jayakumar, S Sakshi, Sreyan Ghosh, Ruohan Gao, Dinesh Manocha Audio-Visual Large Language Models (AVLLMs) are emerging as unified interfaces to multimodal perception. We present the first mechanistic interpretability study of AVLLMs, analyzing how audio and visual features evolve and fuse through different layers of an AVLLM to produce the final text outputs. We find that although AVLLMs encode rich audio semantics at intermediate layers, these capabilities largely fail to surface in the final text generation when audio conflicts with vision. Probing analyses show that useful latent audio information is present, but deeper fusion layers disproportionately privilege visual representations that tend to suppress audio cues. We further trace this imbalance to training: the AVLLM's audio behavior strongly matches its vision-language base model, indicating limited additional alignment to audio supervision. Our findings reveal a fundamental modality bias in AVLLMs and provide new mechanistic insights into how multimodal LLMs integrate audio and vision. Comments: CVPR Findings Subjects: Artificial Intelligence (cs.AI); Sound (cs.SD) Cite as: arXiv:2604.02605 [cs.AI]   (or arXiv:2604.02605v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.02605 Focus to learn more Submission history From: Ramaneswaran Selvakumar [view email] [v1] Fri, 3 Apr 2026 00:48:49 UTC (14,633 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.SD References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)