Reward-RAG: Enhancing RAG with Reward Driven Supervision

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nguyen, Thang, Chin, Peter, Tai, Yu-Wing
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914965340815360
author Nguyen, Thang
Chin, Peter
Tai, Yu-Wing
author_facet Nguyen, Thang
Chin, Peter
Tai, Yu-Wing
contents In this paper, we introduce Reward-RAG, a novel approach designed to enhance the Retrieval-Augmented Generation (RAG) model through Reward-Driven Supervision. Unlike previous RAG methodologies, which focus on training language models (LMs) to utilize external knowledge retrieved from external sources, our method adapts retrieval information to specific domains by employing CriticGPT to train a dedicated reward model. This reward model generates synthesized datasets for fine-tuning the RAG encoder, aligning its outputs more closely with human preferences. The versatility of our approach allows it to be effectively applied across various domains through domain-specific fine-tuning. We evaluate Reward-RAG on publicly available benchmarks from multiple domains, comparing it to state-of-the-art methods. Our experimental results demonstrate significant improvements in performance, highlighting the effectiveness of Reward-RAG in improving the relevance and quality of generated responses. These findings underscore the potential of integrating reward models with RAG to achieve superior outcomes in natural language generation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03780
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reward-RAG: Enhancing RAG with Reward Driven Supervision
Nguyen, Thang
Chin, Peter
Tai, Yu-Wing
Computation and Language
Machine Learning
In this paper, we introduce Reward-RAG, a novel approach designed to enhance the Retrieval-Augmented Generation (RAG) model through Reward-Driven Supervision. Unlike previous RAG methodologies, which focus on training language models (LMs) to utilize external knowledge retrieved from external sources, our method adapts retrieval information to specific domains by employing CriticGPT to train a dedicated reward model. This reward model generates synthesized datasets for fine-tuning the RAG encoder, aligning its outputs more closely with human preferences. The versatility of our approach allows it to be effectively applied across various domains through domain-specific fine-tuning. We evaluate Reward-RAG on publicly available benchmarks from multiple domains, comparing it to state-of-the-art methods. Our experimental results demonstrate significant improvements in performance, highlighting the effectiveness of Reward-RAG in improving the relevance and quality of generated responses. These findings underscore the potential of integrating reward models with RAG to achieve superior outcomes in natural language generation tasks.
title Reward-RAG: Enhancing RAG with Reward Driven Supervision
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2410.03780