Salvato in:
Dettagli Bibliografici
Autori principali: Jeong, Taehee, Zhao, Xingzhe, Li, Peizu, Valvur, Markus, Zhao, Weihua
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2602.07297
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911430491504640
author Jeong, Taehee
Zhao, Xingzhe
Li, Peizu
Valvur, Markus
Zhao, Weihua
author_facet Jeong, Taehee
Zhao, Xingzhe
Li, Peizu
Valvur, Markus
Zhao, Weihua
contents Retrieval Augmented Generation (RAG) is a promising technique for mitigating two key limitations of large language models (LLMs): outdated information and hallucinations. RAG system stores documents as embedding vectors in a database. Given a query, search is executed to find the most related documents. Then, the topmost matching documents are inserted into LLMs' prompt to generate a response. Efficient and accurate searching is critical for RAG to get relevant information. We propose a cost-effective searching algorithm for retrieval process. Our progressive searching algorithm incrementally refines the candidate set through a hierarchy of searches, starting from low-dimensional embeddings and progressing into a higher, target-dimensionality. This multi-stage approach reduces retrieval time while preserving the desired accuracy. Our findings demonstrate that progressive search in RAG systems achieves a balance between dimensionality, speed, and accuracy, enabling scalable and high-performance retrieval even for large databases.
format Preprint
id arxiv_https___arxiv_org_abs_2602_07297
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Progressive Searching for Retrieval in RAG
Jeong, Taehee
Zhao, Xingzhe
Li, Peizu
Valvur, Markus
Zhao, Weihua
Information Retrieval
Artificial Intelligence
Retrieval Augmented Generation (RAG) is a promising technique for mitigating two key limitations of large language models (LLMs): outdated information and hallucinations. RAG system stores documents as embedding vectors in a database. Given a query, search is executed to find the most related documents. Then, the topmost matching documents are inserted into LLMs' prompt to generate a response. Efficient and accurate searching is critical for RAG to get relevant information. We propose a cost-effective searching algorithm for retrieval process. Our progressive searching algorithm incrementally refines the candidate set through a hierarchy of searches, starting from low-dimensional embeddings and progressing into a higher, target-dimensionality. This multi-stage approach reduces retrieval time while preserving the desired accuracy. Our findings demonstrate that progressive search in RAG systems achieves a balance between dimensionality, speed, and accuracy, enabling scalable and high-performance retrieval even for large databases.
title Progressive Searching for Retrieval in RAG
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2602.07297