Paper 2605.20266
A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook
- Published
- May 2026
- Research lab
- Independent
- Citations
- 4
- GitHub
- 258 stars
01 In brief
Summary
This survey provides a comprehensive analysis of Large Audio Language Models (LALMs), focusing on their generalization, trustworthiness, and future outlook.
It examines the endogenous mechanisms of LALMs, including architectural foundations, representational paradigms, training and alignment strategies, and emergent reasoning mechanisms.
The survey establishes a taxonomy of trustworthiness across six pillars: hallucination, robustness, safety, privacy, fairness, and authentication.
It identifies critical vulnerabilities such as cross-modal jailbreaking, latent acoustic backdoors, and biometric privacy leakage, and reviews state-of-the-art LALMs and evaluation benchmarks.
The authors highlight a significant imbalance between mature offensive research and underdeveloped defenses, and propose a roadmap advocating for 'Defense-in-Depth' architectures, causal auditory world modeling, and intrinsic representation engineering to develop more reliable and trustworthy audio intelligence.
02 From the paper
Abstract
Advances in Large Language Models (LLMs) have paved the way for Multimodal Large Language Models (MLLMs). Among these, 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 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 LALMs through six analytical pillars: hallucination, robustness, safety, privacy, fairness, and authentication. The pronounced imbalance between a mature offensive landscape and underdeveloped defenses highlights persistent trustworthiness gaps and multidimensional risks in audio-centric intelligence. Finally, we propose a roadmap advocating for ``Defense-in-Depth'' architectures, causal auditory world modeling, and intrinsic representation engineering to support the development of more reliable and trustworthy audio intelligence. Our project has been uploaded to GitHub https://github.com/Kwwwww74/Awesome-Trustworthy-AudioLLMs.