Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking

About

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

Shengbo Gong, Xianfeng Tang, Qi He, Carl Yang, Wei jin• 2025

Related benchmarks

TaskDatasetResultRank
Question Answering2Wiki
EM69.3
260
Question AnsweringPopQA
EM56.6
112
Question AnsweringMuSiQue
EM39.1
57
Question Answeringmedical--
31
Question AnsweringStory
Exact Match (EM)46.7
14
Showing 5 of 5 rows

Other info

Follow for update