Better Retrieval, Worse Robustness: How Multi-hop RAG Amplifies Upstream ASR Errors

arXiv:2608.22872 · cs.CL, cs.IR, eess.AS · Submitted 2026-08-24 · Read on arXiv

cs.CL, cs.IR, eess.AS

Submitted: 2026-08-24

Updated: 2026-08-25

Comments: Accepted to EMNLP 2026 (Main Conference)

Code: https://github.com/Continuum-AI-Corp/spoken-multihop-rag

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• RAG — 81× in this paper · explained in 3 episodes
• Benchmark — 25× in this paper · explained in 2 episodes
• Robustness — 4× in this paper · explained in 5 episodes
• Decode — 3× in this paper · explained in 2 episodes
• F1 Score — 3× in this paper · explained in 3 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Knowledge Graph — 2× in this paper · explained in 7 episodes
• Retrieval-Augmented Generation (RAG) — 2× in this paper · explained in 16 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Word Error Rate — 2× in this paper
• Accountability — 1× in this paper · explained in 2 episodes
• Algorithmic Bias — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Automatic Speech Recognition (ASR) — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Continual Learning — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• F1 and Exact Match — 1× in this paper
• Generalizability — 1× in this paper · explained in 6 episodes
• Multi-hop Reasoning — 1× in this paper · explained in 3 episodes

Sources

• Global Performance Disparities Between English-Language Accents in Automatic Speech Recognition
• From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
• Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension
• Can Generative Large Language Models Perform ASR Error Correction?
• Seamless: Multilingual Expressive and Streaming Speech Translation
• Towards Data Distillation for End-to-end Spoken Conversational Question Answering

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering