How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation
AI 摘要
该论文研究LLM中的听觉知识对LALM性能的影响,并进行了全面的评估。
主要贡献
- 评估了不同LLM的听觉知识储备
- 揭示了文本预训练中的听觉知识与LALM性能的相关性
- 为LLM在音频研究中的应用提供了实证依据
方法论
通过听觉知识基准测试、级联评估和音频对齐评估,对比分析不同LLM的听觉知识及对LALM性能的影响。
原文摘要
Large language models (LLMs) have been widely used as knowledge backbones of Large Audio Language Models (LALMs), yet how much auditory knowledge they encode through text-only pre-training and how this affects downstream performance remains unclear. We study this gap by comparing different LLMs under two text-only and one audio-grounded setting: (1) direct probing on AKB-2000, a curated benchmark testing the breadth and depth of auditory knowledge; (2) cascade evaluation, where LLMs reason over text descriptions from an audio captioner; and (3) audio-grounded evaluation, where each LLM is fine-tuned into a Large Audio Language Model (LALM) with an audio encoder. Our findings reveal that auditory knowledge varies substantially across families, and text-only results are strongly correlated with audio performance. Our work provides empirical grounding for a comprehensive understanding of LLMs in audio research.