Better Retrieval, Worse Robustness:How Multi-hop RAG Amplifies Upstream ASR Errors
- 类型:arxiv
- 标识:2608.22872
- 链接:https://arxiv.org/abs/2608.22872
- 主分类:rag
- 形态:benchmark
- TLDR:Speech-based applications pass spoken queries through automatic speech recognition (ASR) before any retrieval module, so ASR errors enter the pipeline as a fixed upstream constraint. We empirically test whether two extensions to standard retrieval-augmented generation (RAG), entity-graph linking and iterative reformulation, absorb or amplify these errors. Using four English accents synthesized through neural TTS, we evaluate four RAG configurations on three multi-hop QA benchmarks (HotpotQA, 2WikiMultiHopQA and MuSiQue) against a clean-text oracle. Although the structurally richer configuratio
- 副分类:multimodal
- 待LLM分类:否
- 标题中文:更优检索,更差鲁棒性:多跳 RAG 如何放大上游 ASR 错误
- TLDR中文:基于语音的应用在接入检索模块之前需先通过自动语音识别(ASR)处理口头查询,因此 ASR 错误会以固定的上游约束进入 pipeline。我们通过实验验证标准检索增强生成(RAG)的两项扩展——实体图链接与迭代式 query 改写——是吸收还是放大了这些错误。基于神经 TTS 合成的四种英语口音,我们在三个多跳 QA 基准(HotpotQA、2WikiMultiHopQA 和 MuSiQue)上评测四种 RAG 配置,以干净文本 oracle 为对照。尽管结构上更丰富的 configuratio
- 来源文件:
- /inbox/tom/_candidates/2026-08-25-agent-rag-longcontext-candidates.json