Retrieval-augmented large language models (R-LLMs) combine pre-trained large language models (LLMs) with information retrieval systems to improve the accuracy of factual question-answering. However, current libraries for building R-LLMs provide high-level abstractions without sufficient transparency for evaluating and optimizing prompts within specific inference processes such as retrieval and generation. To address this gap, we present RaLLe, an open-source framework designed to facilitate the development, evaluation, and optimization of R-LLMs for knowledge-intensive tasks. With RaLLe, developers can easily develop and evaluate R-LLMs, improving hand-crafted prompts, assessing individual inference processes, and objectively measuring overall system performance quantitatively. By leveraging these features, developers can enhance the performance and accuracy of their R-LLMs in knowledge-intensive generation tasks. We open-source our code at https://github.com/yhoshi3/RaLLe.
@article{arxiv.2308.10633,
title = {RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models},
author = {Yasuto Hoshi and Daisuke Miyashita and Youyang Ng and Kento Tatsuno and Yasuhiro Morioka and Osamu Torii and Jun Deguchi},
journal= {arXiv preprint arXiv:2308.10633},
year = {2023}
}
Comments
18 pages, 2 figures, see https://youtu.be/JYbm75qnfTg for the demonstration screencast, accepted by EMNLP 2023 System Demonstrations