BERGEN: A Benchmarking Library for Retrieval-Augmented Generation

David Rau, Hervé Déjean, Nadezhda Chirkova, Thibault Formal, Shuai Wang, Stéphane Clinchant, Vassilina Nikoulina


Abstract
Retrieval-Augmented Generation allows to enhance Large Language Models with external knowledge. In response to the recent popularity of generative LLMs, many RAG approaches have been proposed, which involve an intricate number of different configurations such as evaluation datasets, collections, metrics, retrievers, and LLMs. Inconsistent benchmarking poses a major challenge in comparing approaches and understanding the impact of each component in the pipeline. In this work, we study best practices that lay the groundwork for a systematic evaluation of RAG and present BERGEN, an end-to-end library for reproducible research standardizing RAG experiments. In an extensive study focusing on QA, we benchmark different state-of-the-art retrievers, rerankers, and LLMs. Additionally, we analyze existing RAG metrics and datasets.
Anthology ID:
2024.findings-emnlp.449
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7640–7663
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.449/
DOI:
10.18653/v1/2024.findings-emnlp.449
Bibkey:
Cite (ACL):
David Rau, Hervé Déjean, Nadezhda Chirkova, Thibault Formal, Shuai Wang, Stéphane Clinchant, and Vassilina Nikoulina. 2024. BERGEN: A Benchmarking Library for Retrieval-Augmented Generation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 7640–7663, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
BERGEN: A Benchmarking Library for Retrieval-Augmented Generation (Rau et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.449.pdf