@inproceedings{zhang-etal-2026-rsa,
    title = "{RSA}-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios",
    author = "Zhang, Yibo  and
      Luo, Kaiwen  and
      Lin, Liang  and
      Yan, Shilinlu  and
      Wang, Jin  and
      Guo, Yaoqi  and
      Chen, Yitian  and
      Qin, Yalan  and
      Zhou, Zhenhong  and
      Wang, Kun  and
      Sun, Li",
    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.913/",
    pages = "18350--18374",
    ISBN = "979-8-89176-395-1",
    abstract = "While Audio Large Models (ALLMs) have achieved remarkable proficiency, their robustness remains brittle in real-world deployment. Existing evaluations largely rely on synthetic Gaussian noise or simplistic single-source interference, failing to capture the intricate, multi-layered acoustic dynamics{---}or ``Acoustic Ecology''{---}that characterize authentic physical environments. To bridge this ecological gap, we introduce RSA-Bench, a comprehensive robustness benchmark designed to stress-test ALLMs through high-fidelity auditory scene simulations. Unlike traditional methods, we construct evaluation samples by naturally superimposing diverse environmental soundscapes{---}spanning Pasture, Extreme Weather, Classroom, and Outdoors{---}onto clean speech signals across a spectrum of interference intensities. By evaluating models on six core tasks ranging from fundamental perception to complex reasoning, our study unveils three macro-level insights: (I) The Perception-Cognition Gap: Models maintain relative resilience in low-level recognition but suffer a functional collapse in high-order reasoning tasks under stress; (II) Scenario Sensitivity: ``Vocal-like'' interference (e.g., children playing) proves significantly more destructive than mechanical noise, challenging the model{'}s auditory attention mechanisms; and (III) The Denoising Paradox: Standard speech enhancement often exacerbates performance degradation, as ALLMs prove highly sensitive to the semantic distortions introduced by denoising artifacts."
}