Multifaceted Evaluation of Audio-Visual Capability for MLLMs: Effectiveness, Efficiency, Generalizability and Robustness

Yusheng Zhao, Xiao Luo, Junyu Luo, Weizhi Zhang, Zhiping Xiao, Wei Ju, Philip S. Yu, Ming Zhang


Abstract
Multi-modal large language models (MLLMs) have recently achieved great success in processing and understanding information from diverse modalities (e.g., text, audio, and visual signals). Despite their growing popularity, there remains a lack of comprehensive evaluation measuring the audio-visual capabilities of these models, especially in diverse scenarios (e.g., distribution shifts and adversarial attacks). In this paper, we present a multifaceted evaluation of the audio-visual capability of MLLMs, focusing on four key dimensions: effectiveness, efficiency, generalizability, and robustness. Through extensive experiments, we find that MLLMs exhibit strong zero-shot and few-shot generalization abilities, enabling them to achieve great performance with limited data. However, their success relies heavily on the vision modality, which impairs performance when visual input is corrupted or missing. Additionally, while MLLMs are susceptible to adversarial samples, they demonstrate greater robustness compared to traditional models. The experimental results and our observations provide new insights into the audio-visual capabilities of MLLMs, highlighting areas for improvement and offering guidance for future research.
Anthology ID:
2025.findings-emnlp.54
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1026–1041
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.54/
DOI:
Bibkey:
Cite (ACL):
Yusheng Zhao, Xiao Luo, Junyu Luo, Weizhi Zhang, Zhiping Xiao, Wei Ju, Philip S. Yu, and Ming Zhang. 2025. Multifaceted Evaluation of Audio-Visual Capability for MLLMs: Effectiveness, Efficiency, Generalizability and Robustness. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 1026–1041, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Multifaceted Evaluation of Audio-Visual Capability for MLLMs: Effectiveness, Efficiency, Generalizability and Robustness (Zhao et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.54.pdf
Checklist:
 2025.findings-emnlp.54.checklist.pdf