@inproceedings{zhang-etal-2026-beyond-transcription,
    title = "Beyond Transcription: Unified Audio Schema for Perception-Aware {A}udio{LLM}s",
    author = "Zhang, Linhao  and
      Song, Yuhan  and
      Liu, Aiwei  and
      Wu, Chuhan  and
      Zhang, Sijun  and
      Jia, Wei  and
      Liu, Yuan  and
      Wang, Houfeng  and
      Xiao, Zhou",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.967/",
    pages = "19375--19390",
    ISBN = "979-8-89176-395-1",
    abstract = "Recent Audio Large Language Models (AudioLLMs) exhibit a striking performance inversion: while excelling at complex reasoning tasks, they consistently underperform on fine-grained acoustic perception. We attribute this gap to a fundamental limitation of ASR-centric training, which provides precise linguistic targets but implicitly teaches models to suppress paralinguistic cues and acoustic events as noise. To address this, we propose Unified Audio Schema (UAS), a holistic and structured supervision framework that organizes audio information into three explicit components{---}Transcription, Paralinguistics, and Non-linguistic Events{---}within a unified JSON format. This design achieves comprehensive acoustic coverage without sacrificing the tight audio-text alignment that enables reasoning. We validate the effectiveness of this supervision strategy by applying it to both discrete and continuous AudioLLM architectures. Extensive experiments on MMSU, MMAR, and MMAU demonstrate that UAS-Audio yields consistent improvements, boosting fine-grained perception by 10.9{\%} on MMSU over the same-size state-of-the-art models while preserving robust reasoning capabilities. Our code and model are publicly available at https://github.com/Tencent/Unified{\_}Audio{\_}Schema."
}