Retrieval-Augmented Generation (RAG) enhances LLM factuality, but multi-domain applications face challenges like lack of diverse benchmarks and poor out-of-domain generalization. The first contribution of this work is to introduce a diverse benchmark comprising a variety of question-answering tasks from 8 sources and covering 13 domains. Our second contribution consists in systematically testing out-of-domain generalization for typical RAG tuning strategies. While our findings reveal that standard fine-tuning fails to generalize effectively, we show that sequence-level distillation with teacher-generated labels improves out-of-domain performance by providing more coherent supervision. Our findings highlight key strategies for improving multi-domain RAG robustness.
@article{arxiv.2504.02411,
title = {Adapting Large Language Models for Multi-Domain Retrieval-Augmented-Generation},
author = {Alexandre Misrahi and Nadezhda Chirkova and Maxime Louis and Vassilina Nikoulina},
journal= {arXiv preprint arXiv:2504.02411},
year = {2025}
}