[Paper Review] 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 Applications10 citations

TL;DR

The paper proposes a method to implement generative AI services using an enterprise data–based LLM architecture, introducing a Retrieval-Augmented Generation (RAG) model to enhance data storage, retrieval, and content generation in enterprise settings.

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.

Motivation & Objective

• Address information scarcity in enterprise data for generative AI applications.
• Propose remedies such as fine-tuning and direct document integration to mitigate data不足.
• Develop a Retrieval-Augmented Generation (RAG) model to enhance information storage and retrieval for content generation.

Proposed method

• Utilize fine-tuning and direct document integration to address data insufficiency in enterprise contexts.
• Design and implement a Retrieval-Augmented Generation (RAG) model to improve storage and retrieval of information for generation tasks.
• Outline the key phases of the information storage and retrieval methodology underpinning the RAG model.
• Provide illustrative examples to demonstrate applicability in enterprise LLM services.

Experimental results

Research questions

• RQ1 How can data scarcity in enterprise environments be mitigated for effective generative AI services?
• RQ2 What role do fine-tuning and direct document integration play in enhancing enterprise LLM performance?
• RQ3 How can a Retrieval-Augmented Generation (RAG) model be designed to improve information storage, retrieval, and content generation in enterprise settings?

Key findings

• A RAG-based approach is proposed to tackle data insufficiency and improve content generation.
• The study emphasizes the effectiveness of the RAG model for information storage and retrieval in enterprise LLM applications.
• Illustrative instances demonstrate practical applicability of the proposed method in corporate settings.
• The work contributes to improving data-driven content generation and active utilization of LLM-based services in enterprises.