Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yuhang, Hu, Xueyu, Zhang, Shengyu, Chen, Jingyuan, Wu, Fan, Wu, Fei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915007585845248
author Liu, Yuhang
Hu, Xueyu
Zhang, Shengyu
Chen, Jingyuan
Wu, Fan
Wu, Fei
author_facet Liu, Yuhang
Hu, Xueyu
Zhang, Shengyu
Chen, Jingyuan
Wu, Fan
Wu, Fei
contents Retrieval-Augmented Generation (RAG) has proven to be an effective method for mitigating hallucination issues inherent in large language models (LLMs). Previous approaches typically train retrievers based on semantic similarity, lacking optimization for RAG. More recent works have proposed aligning retrievers with the preference signals of LLMs. However, these preference signals are often difficult for dense retrievers, which typically have weaker language capabilities, to understand and learn effectively. Drawing inspiration from pedagogical theories like Guided Discovery Learning, we propose a novel framework, FiGRet (Fine-grained Guidance for Retrievers), which leverages the language capabilities of LLMs to construct examples from a more granular, information-centric perspective to guide the learning of retrievers. Specifically, our method utilizes LLMs to construct easy-to-understand examples from samples where the retriever performs poorly, focusing on three learning objectives highly relevant to the RAG scenario: relevance, comprehensiveness, and purity. These examples serve as scaffolding to ultimately align the retriever with the LLM's preferences. Furthermore, we employ a dual curriculum learning strategy and leverage the reciprocal feedback between LLM and retriever to further enhance the performance of the RAG system. A series of experiments demonstrate that our proposed framework enhances the performance of RAG systems equipped with different retrievers and is applicable to various LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2411_03957
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation
Liu, Yuhang
Hu, Xueyu
Zhang, Shengyu
Chen, Jingyuan
Wu, Fan
Wu, Fei
Information Retrieval
Artificial Intelligence
Retrieval-Augmented Generation (RAG) has proven to be an effective method for mitigating hallucination issues inherent in large language models (LLMs). Previous approaches typically train retrievers based on semantic similarity, lacking optimization for RAG. More recent works have proposed aligning retrievers with the preference signals of LLMs. However, these preference signals are often difficult for dense retrievers, which typically have weaker language capabilities, to understand and learn effectively. Drawing inspiration from pedagogical theories like Guided Discovery Learning, we propose a novel framework, FiGRet (Fine-grained Guidance for Retrievers), which leverages the language capabilities of LLMs to construct examples from a more granular, information-centric perspective to guide the learning of retrievers. Specifically, our method utilizes LLMs to construct easy-to-understand examples from samples where the retriever performs poorly, focusing on three learning objectives highly relevant to the RAG scenario: relevance, comprehensiveness, and purity. These examples serve as scaffolding to ultimately align the retriever with the LLM's preferences. Furthermore, we employ a dual curriculum learning strategy and leverage the reciprocal feedback between LLM and retriever to further enhance the performance of the RAG system. A series of experiments demonstrate that our proposed framework enhances the performance of RAG systems equipped with different retrievers and is applicable to various LLMs.
title Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2411.03957