Papers
arxiv:2410.20753

PlantimesRAG: Planning-guided Retrieval Augmented Generation

Published on Oct 28
Authors:
,
,
,
,

Abstract

We introduce Planning-guided Retrieval Augmented Generation (PlantimesRAG), a novel framework that augments the retrieve-then-reason paradigm of existing RAG frameworks to plan-then-retrieve. PlantimesRAG 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), PlantimesRAG incorporates frozen LMs as plug-and-play experts to generate high-quality answers. Compared to existing RAG solutions, PlantimesRAG demonstrates significant improvements in reducing hallucinations and bolstering attribution due to its structured sub-query decomposition. Overall, PlantimesRAG offers a new perspective on integrating external knowledge in LMs while ensuring attribution by design, contributing towards more reliable LM-based systems.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2410.20753 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2410.20753 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2410.20753 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.