Leveraging the Domain Adaptation of Retrieval Augmented Generation Models for Question Answering and Reducing Hallucination

TL;DR

This paper explores how domain adaptation improves Retrieval Augmented Generation models for question answering in specialized domains, notably reducing hallucinations and enhancing accuracy, demonstrated through experiments on a new hotel-related dataset.

Contribution

It introduces a comprehensive evaluation of domain adaptation effects on RAG architectures for domain-specific QA and addresses hallucination reduction, which was previously underexplored.

Findings

Domain adaptation improves QA performance across RAG models.

It significantly reduces hallucinations in generated responses.

Models trained on domain-specific data outperform general models.

Abstract

While ongoing advancements in Large Language Models have demonstrated remarkable success across various NLP tasks, Retrieval Augmented Generation Model stands out to be highly effective on downstream applications like Question Answering. Recently, RAG-end2end model further optimized the architecture and achieved notable performance improvements on domain adaptation. However, the effectiveness of these RAG-based architectures remains relatively unexplored when fine-tuned on specialized domains such as customer service for building a reliable conversational AI system. Furthermore, a critical challenge persists in reducing the occurrence of hallucinations while maintaining high domain-specific accuracy. In this paper, we investigated the performance of diverse RAG and RAG-like architectures through domain adaptation and evaluated their ability to generate accurate and relevant response grounded in the contextual knowledge base. To facilitate the evaluation of the models, we constructed a novel dataset HotelConvQA, sourced from wide range of hotel-related conversations and fine-tuned all the models on our domain specific dataset. We also addressed a critical research gap on determining the impact of domain adaptation on reducing hallucinations across different RAG architectures, an aspect that was not properly measured in prior work. Our evaluation shows positive results in all metrics by employing domain adaptation, demonstrating strong performance on QA tasks and providing insights into their efficacy in reducing hallucinations. Our findings clearly indicate that domain adaptation not only enhances the models' performance on QA tasks but also significantly reduces hallucination across all evaluated RAG architectures.