| title | A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook |
|---|---|
| authors | Kaiwen Luo, Zhenhong Zhou, Leo Wang, Liang Lin, Yang Xiao, Tianyu Shao, Yuanhe Zhang, Yuxuan Li, Miao Yu, Kailin Lyu, Jiaming Zhang, Dongrui Liu, Li Sun, Yueming Wu, Kai Li, Ting Dang, Xiaojun Jia, Rohan Kumar Das, Xinfeng Li, Siyuan Liang, Qiufeng Wang, Xingjun Ma, Jing Chen, Kun Wang, Junhao Dong, Deqing Zou, Yu Cheng, Xia Hu, Zhigang Zeng, Sen Su, Yang Liu, Yu-Gang Jiang, Philip S. Yu, Yew-Soon Ong |
| date | 2026-05-18 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.20266 |
| affiliation | Nanyang Technological University |
| upvotes | 12 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | The foundational capabilities established by Large Language Models (LLMs) have paved the way for Multimodal Large Language Models (MLLMs), within which Large Audio Language Models (LALMs) are essential for realizing universal auditory intelligence. Despite their remarkable performance, the escalation of LALMs' capabilities has significantly outpaced the development of systemic frameworks to ensure their trustworthiness. This survey provides a comprehensive investigation into the endogenous mechanisms of LALMs, detailing the architectural innovations and alignment algorithms that facilitate emergent reasoning. Specifically, we analyze how the transition to unified end-to-end frameworks and the integration of continuous acoustic signals inherently expand the attack surface. To rigorously evaluate the risks within these paradigms, we establish a comprehensive taxonomy of trustworthiness, categorizing critical vulnerabilities such as cross-modal jailbreaking, latent acoustic backdoors, and biometric privacy leakage. We review the state-of-the-art through six analytical pillars: hallucination, robustness, safety, privacy, fairness, and authentication. The profound imbalance between a mature offensive landscape and underdeveloped defenses further validates the critical trustworthiness gaps and multidimensional risks facing audio-centric intelligence. Finally, we propose a strategic roadmap advocating for "Defense-in-Depth" architectures, causal auditory world modeling, and intrinsic representation engineering to bridge the gap between empirical performance and intrinsically trustworthy audio intelligence. Our project has been uploaded to GitHub https://github.com/Kwwwww74/Awesome-Trustworthy-AudioLLMs. |
cite
@misc{luo2026survey,
title={A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook},
author={Kaiwen Luo and Zhenhong Zhou and Leo Wang and Liang Lin and Yang Xiao and Tianyu Shao and Yuanhe Zhang and Yuxuan Li and Miao Yu and Kailin Lyu and Jiaming Zhang and Dongrui Liu and Li Sun and Yueming Wu and Kai Li and Ting Dang and Xiaojun Jia and Rohan Kumar Das and Xinfeng Li and Siyuan Liang and Qiufeng Wang and Xingjun Ma and Jing Chen and Kun Wang and Junhao Dong and Deqing Zou and Yu Cheng and Xia Hu and Zhigang Zeng and Sen Su and Yang Liu and Yu-Gang Jiang and Philip S. Yu and Yew-Soon Ong},
year={2026},
eprint={2605.20266},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.20266}
}