arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.10656eess.AScs.SD
收藏

AudioRAG:一个用于音频推理和信息检索的挑战性基准

AudioRAG: A Challenging Benchmark for Audio Reasoning and Information Retrieval

Jingru Lin, Chen Zhang, Tianrui Wang, Haizhou Li

AI总结:

AudioRAG是一个用于评估音频推理和信息检索能力的挑战性基准,通过整合检索增强生成技术,为未来研究提供更强大的基准。

摘要:

由于近期在大音频-语言模型(LALMs)上的进展,这些模型在声音、语音和音乐相关任务中表现出色,因此提出了评估这些模型的基准。现有基准通常只关注内部知识推理,忽视了需要外部信息支撑的真实场景。为弥合这一差距,我们引入AudioRAG,一个新型基准,旨在评估基于音频的推理并结合信息检索的现实网络环境。该基准包含由LLM生成和人工整理的问题-答案对。我们的评估发现,即使是最先进的LALMs也难以回答这些问题。因此,我们提出一个整合音频推理与检索增强生成的代理流程,为未来研究提供更坚实的基准。

英文摘要:

Due to recent advancements in Large Audio-Language Models (LALMs) that demonstrate remarkable performance across a range of sound-, speech- and music-related tasks, there is a growing interest in proposing benchmarks to assess these models. Existing benchmarks generally focus only on reasoning with internal knowledge, neglecting real-world scenarios that require external information grounding. To bridge this gap, we introduce AudioRAG, a novel benchmark designed to evaluate audio-based reasoning augmented by information retrieval in realistic web environments. This benchmark comprises both LLM-generated and manually curated question-answer pairs. Our evaluations reveal that even the state-of-the-art LALMs struggle to answer these questions. We therefore propose an agentic pipeline that integrates audio reasoning with retrieval-augmented generation, providing a stronger baseline for future research.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑