# 多跳 RAG 如何放大上游 ASR 错误：实体图谱链接与迭代改写反而加剧鲁棒性下降

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-24 08:00
- AIHOT 分数：66
- AIHOT 链接：https://aihot.virxact.com/items/cmt89ixa72xy9ro73leplhxiw
- 原文链接：https://arxiv.org/abs/2608.22872

## AI 摘要

研究测试了实体图谱链接与迭代改写两种 RAG 扩展在 ASR 输入下的表现。在 HotpotQA、2WikiMultiHopQA 和 MuSiQue 三个多跳问答基准上，两种扩展均放大错误：干净文本与最高 WER 口音间的 F1 差距比朴素稠密检索大 36-67%。查询实体损坏是主要失败模式，占 2WikiMultiHopQA 上 87-96% 的退化案例。

## 正文

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 configurations generally retain higher absolute F1 under ASR input, both extensions amplify the error: the F1 gap from clean text to the highest-WER accent is 36-67% larger under their combination than under naive dense retrieval, on all three benchmarks. The dominant failure mode is corruption of one or more query entities, accounting for 87-96% of degradation cases on 2WikiMultiHopQA across all four methods. Two lightweight surface-form mitigations leave most of the gap intact, indicating that downstream retrieval structure amplifies remaining entity errors. We release code and data at https://github.com/ZhenghuaBao/spoken-multihop-rag .