Retrieval-Generation Synergy Augmented Large Language Models

TL;DR

This paper introduces an iterative retrieval-generation framework that enhances large language models' reasoning capabilities by effectively combining parametric and non-parametric knowledge through collaborative interactions, improving performance on complex question answering tasks.

Contribution

The paper presents a novel iterative retrieval-generation approach that leverages both knowledge sources and improves multi-step reasoning in large language models.

Findings

Significant improvement in reasoning ability on QA datasets

Outperforms previous baseline methods

Effective for both single-hop and multi-hop QA tasks

Abstract

Large language models augmented with task-relevant documents have demonstrated impressive performance on knowledge-intensive tasks. However, regarding how to obtain effective documents, the existing methods are mainly divided into two categories. One is to retrieve from an external knowledge base, and the other is to utilize large language models to generate documents. We propose an iterative retrieval-generation collaborative framework. It is not only able to leverage both parametric and non-parametric knowledge, but also helps to find the correct reasoning path through retrieval-generation interactions, which is very important for tasks that require multi-step reasoning. We conduct experiments on four question answering datasets, including single-hop QA and multi-hop QA tasks. Empirical results show that our method significantly improves the reasoning ability of large language models and outperforms previous baselines.