arXiv cs.CL· Hua-Hsuan Chen, Xuanjun Chen, Wei-Chung Lu, Chih-Kai Yang, Yu-Xiang Lin, Sung-Feng Huang, Haibin Wu, Hung-yi Lee·· 3 天前AI 评分37
LALM 后训练究竟学到了什么？重新审视音频理解与推理能力
What Does LALM Post-training Learn? Rethinking Audio Understanding and Reasoning Capabilities
AI 导读
针对大型音频语言模型（LALM）后训练带来的性能提升，受控实验发现这些提升大多并非来自音频理解与推理能力的真实进步：即使没有有效音频信息，提升依然存在，而一旦更换问题格式，提升便基本消失。这表明后训练更多是让模型利用任务特定的文本线索和答题模式，而非习得可泛化的音频理解与推理能力。
正文 · 原文
Abstract:Post-training often improves the performance of large audio-language models on audio understanding and reasoning benchmarks. However, these improvements may reflect adaptation to specific question formats, such as multiple-choice questions, rather than genuine advances in audio understanding and reasoning capabilities. To investigate what LALMs actually learn from post-training, we conduct controlled experiments that disentangle improvements in audio understanding from adaptation to specific question formats. Across different models and post-training methods, we find that much of the reported improvement persists even without informative audio, but largely disappears when the question format changes. These findings suggest that post-training often teaches models to exploit task-specific textual cues and answer patterns rather than developing generalizable audio understanding and reasoning capabilities.
| Comments: | Work in progress |
| Subjects: | Sound (cs.SD); Computation and Language (cs.CL); Multimedia (cs.MM); Audio and Speech Processing (eess.AS) |
| Cite as: | arXiv:2610.19476 [cs.SD] |
| (or arXiv:2610.19476v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19476 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xuanjun Chen [view email]
[v1]
Wed, 14 Oct 2026 02:54:57 UTC (4,784 KB)
来源：arXiv cs.CL · arxiv.org