BERGEN: A Benchmarking Library for Retrieval-Augmented Generation

TL;DR

BERGEN is an open-source benchmarking library designed to standardize and facilitate reproducible evaluation of Retrieval-Augmented Generation systems, enabling fair comparison of different components like retrievers, rerankers, and LLMs.

Contribution

This work introduces BERGEN, a comprehensive library that standardizes RAG benchmarking, addressing inconsistencies and enabling systematic evaluation of retrieval and generation components.

Findings

Benchmarking different retrievers, rerankers, and LLMs for QA.

Analysis of RAG metrics and datasets.

Identification of best practices for RAG evaluation.

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. Our open-source library BERGEN is available under \url{https://github.com/naver/bergen}.