[论文解读] A Study on the Implementation of Generative AI Services Using an Enterprise Data-Based LLM Application Architecture

C. Jeong|arXiv (Cornell University)|Sep 3, 2023

Robotic Process Automation Applications被引用 10

一句话总结

本文提出一种使用基于企业数据的 LLM 架构实现生成式 AI 服务的方法，引入 Retrieval-Augmented Generation (RAG) 模型，以提升企业环境中的数据存储、检索与内容生成。

ABSTRACT

This study presents a method for implementing generative AI services by utilizing the Large Language Models (LLM) application architecture. With recent advancements in generative AI technology, LLMs have gained prominence across various domains. In this context, the research addresses the challenge of information scarcity and proposes specific remedies by harnessing LLM capabilities. The investigation delves into strategies for mitigating the issue of inadequate data, offering tailored solutions. The study delves into the efficacy of employing fine-tuning techniques and direct document integration to alleviate data insufficiency. A significant contribution of this work is the development of a Retrieval-Augmented Generation (RAG) model, which tackles the aforementioned challenges. The RAG model is carefully designed to enhance information storage and retrieval processes, ensuring improved content generation. The research elucidates the key phases of the information storage and retrieval methodology underpinned by the RAG model. A comprehensive analysis of these steps is undertaken, emphasizing their significance in addressing the scarcity of data. The study highlights the efficacy of the proposed method, showcasing its applicability through illustrative instances. By implementing the RAG model for information storage and retrieval, the research not only contributes to a deeper comprehension of generative AI technology but also facilitates its practical usability within enterprises utilizing LLMs. This work holds substantial value in advancing the field of generative AI, offering insights into enhancing data-driven content generation and fostering active utilization of LLM-based services within corporate settings.

研究动机与目标

• 解决企业数据中信息稀缺以支撑生成式 AI 应用。
• 提出如微调和直接文档集成等解决方案来缓解 data不足。
• 开发一个 Retrieval-Augmented Generation (RAG) 模型，以提升信息存储与检索用于内容生成。

提出的方法

• 在企业场景中利用微调和直接文档集成来解决数据不足。
• 设计并实现一个 Retrieval-Augmented Generation (RAG) 模型，以改进信息的存储与检索以完成生成任务。
• 概述支撑 RAG 模型的信息存储与检索方法论的关键阶段。
• 提供示例以展示在企业 LLM 服务中的适用性。

实验结果

研究问题

• RQ1 如何缓解企业环境中的数据稀缺，以实现有效的生成式 AI 服务？
• RQ2 微调和直接文档集成在提升企业 LLM 性能方面扮演怎样的角色？
• RQ3 如何设计 Retrieval-Augmented Generation (RAG) 模型以改善企业环境中的信息存储、检索与内容生成？

主要发现

• 提出了一种基于 RAG 的方法，以解决数据不足并提升内容生成。
• 研究强调 RAG 模型在企业 LLM 应用中信息存储与检索的有效性。
• 示例实例展示了所提方法在企业环境中的实际适用性。
• 该工作有助于提升数据驱动的内容生成以及在企业中主动利用基于 LLM 的服务。