Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation

TL;DR

This paper introduces InFO-RAG, an unsupervised training method that enhances large language models' ability to refine and utilize retrieved information effectively across diverse tasks, improving performance and robustness.

Contribution

It proposes a novel unsupervised training approach, InFO-RAG, that treats LLMs as information refiners to better integrate retrieved texts regardless of their quality.

Findings

InFO-RAG improves LLaMA2's performance by 9.39% on average across 11 datasets.

InFO-RAG enhances in-context learning capabilities.

InFO-RAG increases robustness of retrieval-augmented generation.

Abstract

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating additional information from retrieval. However, studies have shown that LLMs still face challenges in effectively using the retrieved information, even ignoring it or being misled by it. The key reason is that the training of LLMs does not clearly make LLMs learn how to utilize input retrieved texts with varied quality. In this paper, we propose a novel perspective that considers the role of LLMs in RAG as ``Information Refiner'', which means that regardless of correctness, completeness, or usefulness of retrieved texts, LLMs can consistently integrate knowledge within the retrieved texts and model parameters to generate the texts that are more concise, accurate, and complete than the retrieved texts. To this end, we propose an information refinement training method named InFO-RAG that optimizes LLMs for RAG in an unsupervised manner. InFO-RAG is low-cost and general across various tasks. Extensive experiments on zero-shot prediction of 11 datasets in diverse tasks including Question Answering, Slot-Filling, Language Modeling, Dialogue, and Code Generation show that InFO-RAG improves the performance of LLaMA2 by an average of 9.39\% relative points. InFO-RAG also shows advantages in in-context learning and robustness of RAG.