Salvato in:
Dettagli Bibliografici
Autori principali: Gong, Shengbo, Tang, Xianfeng, Yang, Carl, jin, Wei
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2508.02435
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909720777850880
author Gong, Shengbo
Tang, Xianfeng
Yang, Carl
jin, Wei
author_facet Gong, Shengbo
Tang, Xianfeng
Yang, Carl
jin, Wei
contents Retrieval-augmented generation (RAG) is critical for reducing hallucinations and incorporating external knowledge into Large Language Models (LLMs). However, advanced RAG systems face a trade-off between performance and efficiency. Multi-round RAG approaches achieve strong reasoning but incur excessive LLM calls and token costs, while Graph RAG methods suffer from computationally expensive, error-prone graph construction and retrieval redundancy. To address these challenges, we propose T$^2$RAG, a novel framework that operates on a simple, graph-free knowledge base of atomic triplets. T$^2$RAG leverages an LLM to decompose questions into searchable triplets with placeholders, which it then iteratively resolves by retrieving evidence from the triplet database. Empirical results show that T$^2$RAG significantly outperforms state-of-the-art multi-round and Graph RAG methods, achieving an average performance gain of up to 11\% across six datasets while reducing retrieval costs by up to 45\%. Our code is available at https://github.com/rockcor/T2RAG
format Preprint
id arxiv_https___arxiv_org_abs_2508_02435
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking
Gong, Shengbo
Tang, Xianfeng
Yang, Carl
jin, Wei
Information Retrieval
H.3
Retrieval-augmented generation (RAG) is critical for reducing hallucinations and incorporating external knowledge into Large Language Models (LLMs). However, advanced RAG systems face a trade-off between performance and efficiency. Multi-round RAG approaches achieve strong reasoning but incur excessive LLM calls and token costs, while Graph RAG methods suffer from computationally expensive, error-prone graph construction and retrieval redundancy. To address these challenges, we propose T$^2$RAG, a novel framework that operates on a simple, graph-free knowledge base of atomic triplets. T$^2$RAG leverages an LLM to decompose questions into searchable triplets with placeholders, which it then iteratively resolves by retrieving evidence from the triplet database. Empirical results show that T$^2$RAG significantly outperforms state-of-the-art multi-round and Graph RAG methods, achieving an average performance gain of up to 11\% across six datasets while reducing retrieval costs by up to 45\%. Our code is available at https://github.com/rockcor/T2RAG
title Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking
topic Information Retrieval
H.3
url https://arxiv.org/abs/2508.02435