When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Yongjie, Yu, Yue, Song, Kaisong, Lin, Jun, Shen, Zhiqi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912640518848512
author Wang, Yongjie
Yu, Yue
Song, Kaisong
Lin, Jun
Shen, Zhiqi
author_facet Wang, Yongjie
Yu, Yue
Song, Kaisong
Lin, Jun
Shen, Zhiqi
contents Large Language Models (LLMs) have enabled a wide range of applications through their powerful capabilities in language understanding and generation. However, as LLMs are trained on static corpora, they face difficulties in addressing rapidly evolving information or domain-specific queries. Retrieval-Augmented Generation (RAG) was developed to overcome this limitation by integrating LLMs with external retrieval mechanisms, allowing them to access up-to-date and contextually relevant knowledge. However, as LLMs themselves continue to advance in scale and capability, the relative advantages of traditional RAG frameworks have become less pronounced and necessary. Here, we present a comprehensive review of RAG, beginning with its overarching objectives and core components. We then analyze the key challenges within RAG, highlighting critical weakness that may limit its effectiveness. Finally, we showcase applications where LLMs alone perform inadequately, but where RAG, when combined with LLMs, can substantially enhance their effectiveness. We hope this work will encourage researchers to reconsider the role of RAG and inspire the development of next-generation RAG systems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09106
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
Wang, Yongjie
Yu, Yue
Song, Kaisong
Lin, Jun
Shen, Zhiqi
Computation and Language
68T50
I.2.7
Large Language Models (LLMs) have enabled a wide range of applications through their powerful capabilities in language understanding and generation. However, as LLMs are trained on static corpora, they face difficulties in addressing rapidly evolving information or domain-specific queries. Retrieval-Augmented Generation (RAG) was developed to overcome this limitation by integrating LLMs with external retrieval mechanisms, allowing them to access up-to-date and contextually relevant knowledge. However, as LLMs themselves continue to advance in scale and capability, the relative advantages of traditional RAG frameworks have become less pronounced and necessary. Here, we present a comprehensive review of RAG, beginning with its overarching objectives and core components. We then analyze the key challenges within RAG, highlighting critical weakness that may limit its effectiveness. Finally, we showcase applications where LLMs alone perform inadequately, but where RAG, when combined with LLMs, can substantially enhance their effectiveness. We hope this work will encourage researchers to reconsider the role of RAG and inspire the development of next-generation RAG systems.
title When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
topic Computation and Language
68T50
I.2.7
url https://arxiv.org/abs/2510.09106