# Adapting Large Language Models for Multi-Domain Retrieval-Augmented-Generation

Source: [Adapting Large Language Models for Multi-Domain Retrieval-Augmented-Generation](<https://www.sota2.com/research/paper/68fa77cc1e209131cea75667>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:26:29.946Z

Authors: Alexandre Misrahi, Nadezhda Chirkova, Maxime Louis, Vassilina Nikoulina

Published: 2025-04-03T09:03:40.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2504.02411>)

[PDF](<https://arxiv.org/pdf/2504.02411.pdf>)
