Plan$\times$RAG: Planning-guided Retrieval Augmented Generation

Autor:	Verma, Prakhar, Midigeshi, Sukruta Prakash, Sinha, Gaurav, Solin, Arno, Natarajan, Nagarajan, Sharma, Amit
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	We introduce Planning-guided Retrieval Augmented Generation (Plan$\times$RAG), a novel framework that augments the \emph{retrieve-then-reason} paradigm of existing RAG frameworks to \emph{plan-then-retrieve}. Plan$\times$RAG formulates a reasoning plan as a directed acyclic graph (DAG), decomposing queries into interrelated atomic sub-queries. Answer generation follows the DAG structure, allowing significant gains in efficiency through parallelized retrieval and generation. While state-of-the-art RAG solutions require extensive data generation and fine-tuning of language models (LMs), Plan$\times$RAG incorporates frozen LMs as plug-and-play experts to generate high-quality answers. Compared to existing RAG solutions, Plan$\times$RAG demonstrates significant improvements in reducing hallucinations and bolstering attribution due to its structured sub-query decomposition. Overall, Plan$\times$RAG offers a new perspective on integrating external knowledge in LMs while ensuring attribution by design, contributing towards more reliable LM-based systems. Comment: 22 pages, preprint
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2410.20753 Zobrazit plný text záznamu View this record from Arxiv