The Distracting Effect: Understanding Irrelevant Passages in RAG

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Amiraz, Chen, Cuconasu, Florin, Filice, Simone, Karnin, Zohar
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908615880736768
author Amiraz, Chen
Cuconasu, Florin
Filice, Simone
Karnin, Zohar
author_facet Amiraz, Chen
Cuconasu, Florin
Filice, Simone
Karnin, Zohar
contents A well-known issue with Retrieval Augmented Generation (RAG) is that retrieved passages that are irrelevant to the query sometimes distract the answer-generating LLM, causing it to provide an incorrect response. In this paper, we shed light on this core issue and formulate the distracting effect of a passage w.r.t. a query (and an LLM). We provide a quantifiable measure of the distracting effect of a passage and demonstrate its robustness across LLMs. Our research introduces novel methods for identifying and using hard distracting passages to improve RAG systems. By fine-tuning LLMs with these carefully selected distracting passages, we achieve up to a 7.5% increase in answering accuracy compared to counterparts fine-tuned on conventional RAG datasets. Our contribution is two-fold: first, we move beyond the simple binary classification of irrelevant passages as either completely unrelated vs. distracting, and second, we develop and analyze multiple methods for finding hard distracting passages. To our knowledge, no other research has provided such a comprehensive framework for identifying and utilizing hard distracting passages.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06914
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Distracting Effect: Understanding Irrelevant Passages in RAG
Amiraz, Chen
Cuconasu, Florin
Filice, Simone
Karnin, Zohar
Computation and Language
Information Retrieval
A well-known issue with Retrieval Augmented Generation (RAG) is that retrieved passages that are irrelevant to the query sometimes distract the answer-generating LLM, causing it to provide an incorrect response. In this paper, we shed light on this core issue and formulate the distracting effect of a passage w.r.t. a query (and an LLM). We provide a quantifiable measure of the distracting effect of a passage and demonstrate its robustness across LLMs. Our research introduces novel methods for identifying and using hard distracting passages to improve RAG systems. By fine-tuning LLMs with these carefully selected distracting passages, we achieve up to a 7.5% increase in answering accuracy compared to counterparts fine-tuned on conventional RAG datasets. Our contribution is two-fold: first, we move beyond the simple binary classification of irrelevant passages as either completely unrelated vs. distracting, and second, we develop and analyze multiple methods for finding hard distracting passages. To our knowledge, no other research has provided such a comprehensive framework for identifying and utilizing hard distracting passages.
title The Distracting Effect: Understanding Irrelevant Passages in RAG
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2505.06914