Retrieval-augmented generation (RAG) enhances the question-answering (QA) abilities of large language models (LLMs) by integrating external knowledge. However, adapting general-purpose RAG systems to specialized fields such as science and medicine poses unique challenges due to distribution shifts and limited access to domain-specific data. To tackle this, we propose SimRAG, a self-training approach that equips the LLM with joint capabilities of question answering and question generation for domain adaptation. Our method first fine-tunes the LLM on instruction-following, question-answering, and search-related data. Then, it prompts the same LLM to generate diverse domain-relevant questions from unlabeled corpora, with an additional filtering strategy to retain high-quality synthetic examples. By leveraging these self-generated synthetic examples, the LLM can improve their performance on domain-specific RAG tasks. Experiments on 11 datasets, spanning two backbone sizes and three domains, demonstrate that SimRAG outperforms baselines by 1.2\%--8.6\%.
@article{arxiv.2410.17952,
title = {SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains},
author = {Ran Xu and Hui Liu and Sreyashi Nag and Zhenwei Dai and Yaochen Xie and Xianfeng Tang and Chen Luo and Yang Li and Joyce C. Ho and Carl Yang and Qi He},
journal= {arXiv preprint arXiv:2410.17952},
year = {2025}
}