arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.00982cs.CL
收藏

LocalRQA:从生成数据到本地训练、测试和部署检索增强型问答系统

LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA Systems

Columbia University(哥伦比亚大学)

Xiao Yu, Yunan Lu, Zhou Yu

AI总结:

本文提出开源工具包 LocalRQA,支持检索增强问答系统的数据生成、本地训练、评估与部署,并证明其训练的 7B 模型可达到接近 OpenAI text-ada-002 与 GPT-4-turbo 的性能。

摘要:

检索增强型问答系统将检索技术与大型语言模型相结合,以提供更准确、信息更丰富的答案。许多现有工具包允许用户使用现成模型快速构建此类系统,但在支持研究人员和开发者定制模型训练、测试与部署流程方面存在不足。我们提出 LocalRQA,这是一个开源工具包,特色在于提供从最新研究中精选的大量模型训练算法、评估方法和部署工具。作为展示,我们使用从 Databricks 和 Faire 网站获取的在线文档构建问答系统。我们发现,使用 LocalRQA 训练并部署的 7B 模型,在性能上与使用 OpenAI 的 text-ada-002 和 GPT-4-turbo 相当。

英文摘要:

Retrieval-augmented question-answering systems combine retrieval techniques with large language models to provide answers that are more accurate and informative. Many existing toolkits allow users to quickly build such systems using off-the-shelf models, but they fall short in supporting researchers and developers to customize the model training, testing, and deployment process. We propose LocalRQA, an open-source toolkit that features a wide selection of model training algorithms, evaluation methods, and deployment tools curated from the latest research. As a showcase, we build QA systems using online documentation obtained from Databricks and Faire's websites. We find 7B-models trained and deployed using LocalRQA reach a similar performance compared to using OpenAI's text-ada-002 and GPT-4-turbo.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑