Saved in:
Bibliographic Details
Main Authors: Seabra, Antony, Cavalcante, Claudio, Nepomuceno, Joao, Lago, Lucas, Ruberg, Nicolaas, Lifschitz, Sergio
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.17942
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929646134624256
author Seabra, Antony
Cavalcante, Claudio
Nepomuceno, Joao
Lago, Lucas
Ruberg, Nicolaas
Lifschitz, Sergio
author_facet Seabra, Antony
Cavalcante, Claudio
Nepomuceno, Joao
Lago, Lucas
Ruberg, Nicolaas
Lifschitz, Sergio
contents We present a question-and-answer (Q\&A) application designed to support the contract management process by leveraging combined information from contract documents (PDFs) and data retrieved from contract management systems (database). This data is processed by a large language model (LLM) to provide precise and relevant answers. The accuracy of these responses is further enhanced through the use of Retrieval-Augmented Generation (RAG), text-to-SQL techniques, and agents that dynamically orchestrate the workflow. These techniques eliminate the need to retrain the language model. Additionally, we employed Prompt Engineering to fine-tune the focus of responses. Our findings demonstrate that this multi-agent orchestration and combination of techniques significantly improve the relevance and accuracy of the answers, offering a promising direction for future information systems.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17942
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Contrato360 2.0: A Document and Database-Driven Question-Answer System using Large Language Models and Agents
Seabra, Antony
Cavalcante, Claudio
Nepomuceno, Joao
Lago, Lucas
Ruberg, Nicolaas
Lifschitz, Sergio
Artificial Intelligence
We present a question-and-answer (Q\&A) application designed to support the contract management process by leveraging combined information from contract documents (PDFs) and data retrieved from contract management systems (database). This data is processed by a large language model (LLM) to provide precise and relevant answers. The accuracy of these responses is further enhanced through the use of Retrieval-Augmented Generation (RAG), text-to-SQL techniques, and agents that dynamically orchestrate the workflow. These techniques eliminate the need to retrain the language model. Additionally, we employed Prompt Engineering to fine-tune the focus of responses. Our findings demonstrate that this multi-agent orchestration and combination of techniques significantly improve the relevance and accuracy of the answers, offering a promising direction for future information systems.
title Contrato360 2.0: A Document and Database-Driven Question-Answer System using Large Language Models and Agents
topic Artificial Intelligence
url https://arxiv.org/abs/2412.17942