@inproceedings{jensen-etal-2026-stochastic,
    title = "Stochastic Parrots or True Virtuosos? Digging Deeper Into the Audio-Video Understanding of {AVQA} Models",
    author = "Jensen, Sara Pernille  and
      Innset Hurum, Hallvard  and
      Christodoulou, Anna-Maria",
    editor = "Epure, Elena V.  and
      Oramas, Sergio  and
      Doh, SeungHeon  and
      Ramoneda, Pedro  and
      Kruspe, Anna  and
      Sordo, Mohamed",
    booktitle = "Proceedings of the 4th Workshop on {NLP} for Music and Audio ({NLP}4{M}us{A} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.nlp4musa-1.3/",
    pages = "13--19",
    ISBN = "979-8-89176-369-2",
    abstract = "Audio-video question answering (AVQA) systems for music show signs of multimodal ``understanding'', but it is unclear which inputs they rely on or whether their behavior reflects genuine audio-video reasoning. Existing evaluations focus on overall accuracy and rarely examine modality dependence. We address this gap by suggesting a method of using counterfactual evaluations to analyse the audio-video understanding of the models, illustrated with a case study on the audio-video spatial-temporal (AVST) architecture. This includes interventions that zero out or swap audio, video, or both, where results are benchmarked against a baseline based on linguistic patterns alone. Results show stronger reliance on audio than video, yet performance persists when either modality is removed, indicating learned cross-modal representations. The AVQA system studied thus exhibits non-trivial multimodal integration, though its ``understanding'' remains uneven."
}