@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-rsa">
<titleInfo>
<title>RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yibo</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaiwen</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shilinlu</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaoqi</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yitian</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yalan</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenhong</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">zhang-etal-2026-rsa</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.913/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>18350</start>
<end>18374</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios
%A Zhang, Yibo
%A Luo, Kaiwen
%A Lin, Liang
%A Yan, Shilinlu
%A Wang, Jin
%A Guo, Yaoqi
%A Chen, Yitian
%A Qin, Yalan
%A Zhou, Zhenhong
%A Wang, Kun
%A Sun, Li
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F zhang-etal-2026-rsa
%X 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.
%U https://aclanthology.org/2026.findings-acl.913/
%P 18350-18374
Markdown (Informal)
[RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios](https://aclanthology.org/2026.findings-acl.913/) (Zhang et al., Findings 2026)
ACL
- Yibo Zhang, Kaiwen Luo, Liang Lin, Shilinlu Yan, Jin Wang, Yaoqi Guo, Yitian Chen, Yalan Qin, Zhenhong Zhou, Kun Wang, and Li Sun. 2026. RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios. In Findings of the Association for Computational Linguistics: ACL 2026, pages 18350–18374, San Diego, California, United States. Association for Computational Linguistics.