Salvato in:
Dettagli Bibliografici
Autori principali: Xiao, Qiao, Tsang, Hong Ting, Bai, Jiaxin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.18667
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912697254150144
author Xiao, Qiao
Tsang, Hong Ting
Bai, Jiaxin
author_facet Xiao, Qiao
Tsang, Hong Ting
Bai, Jiaxin
contents Graph-based Retrieval-augmented generation (RAG) has become a widely studied approach for improving the reasoning, accuracy, and factuality of Large Language Models (LLMs). However, many existing graph-based RAG systems overlook the high cost associated with LLM token usage during graph construction, hindering large-scale adoption. To address this, we propose TERAG, a simple yet effective framework designed to build informative graphs at a significantly lower cost. Inspired by HippoRAG, we incorporate Personalized PageRank (PPR) during the retrieval phase, and we achieve at least 80% of the accuracy of widely used graph-based RAG methods while consuming only 3%-11% of the output tokens. With its low token footprint and efficient construction pipeline, TERAG is well-suited for large-scale and cost-sensitive deployment scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18667
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TERAG: Token-Efficient Graph-Based Retrieval-Augmented Generation
Xiao, Qiao
Tsang, Hong Ting
Bai, Jiaxin
Artificial Intelligence
Graph-based Retrieval-augmented generation (RAG) has become a widely studied approach for improving the reasoning, accuracy, and factuality of Large Language Models (LLMs). However, many existing graph-based RAG systems overlook the high cost associated with LLM token usage during graph construction, hindering large-scale adoption. To address this, we propose TERAG, a simple yet effective framework designed to build informative graphs at a significantly lower cost. Inspired by HippoRAG, we incorporate Personalized PageRank (PPR) during the retrieval phase, and we achieve at least 80% of the accuracy of widely used graph-based RAG methods while consuming only 3%-11% of the output tokens. With its low token footprint and efficient construction pipeline, TERAG is well-suited for large-scale and cost-sensitive deployment scenarios.
title TERAG: Token-Efficient Graph-Based Retrieval-Augmented Generation
topic Artificial Intelligence
url https://arxiv.org/abs/2509.18667