Saved in:
Bibliographic Details
Main Authors: Berdyugina, Daria, Cohen, Anaëlle, Rioual, Yohann
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.24334
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908995356196864
author Berdyugina, Daria
Cohen, Anaëlle
Rioual, Yohann
author_facet Berdyugina, Daria
Cohen, Anaëlle
Rioual, Yohann
contents Standard Retrieval-Augmented Generation (RAG) chunking methods often create excessive redundancy, increasing storage costs and slowing retrieval. This study explores chunk filtering strategies, such as semantic, topic-based, and named-entity-based methods in order to reduce the indexed corpus while preserving retrieval quality. Experiments are conducted on multiple corpora. Retrieval performance is evaluated using a token-based framework based on precision, recall, and intersection-over-union metrics. Results indicate that entity-based filtering can reduce vector index size by approximately 25% to 36% while maintaining high retrieval quality close to the baseline. These findings suggest that redundancy introduced during chunking can be effectively reduced through lightweight filtering, improving the efficiency of retrieval-oriented components in RAG pipelines.
format Preprint
id arxiv_https___arxiv_org_abs_2604_24334
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reducing Redundancy in Retrieval-Augmented Generation through Chunk Filtering
Berdyugina, Daria
Cohen, Anaëlle
Rioual, Yohann
Computation and Language
Standard Retrieval-Augmented Generation (RAG) chunking methods often create excessive redundancy, increasing storage costs and slowing retrieval. This study explores chunk filtering strategies, such as semantic, topic-based, and named-entity-based methods in order to reduce the indexed corpus while preserving retrieval quality. Experiments are conducted on multiple corpora. Retrieval performance is evaluated using a token-based framework based on precision, recall, and intersection-over-union metrics. Results indicate that entity-based filtering can reduce vector index size by approximately 25% to 36% while maintaining high retrieval quality close to the baseline. These findings suggest that redundancy introduced during chunking can be effectively reduced through lightweight filtering, improving the efficiency of retrieval-oriented components in RAG pipelines.
title Reducing Redundancy in Retrieval-Augmented Generation through Chunk Filtering
topic Computation and Language
url https://arxiv.org/abs/2604.24334