Contrato360 2.0: A Document and Database-Driven Question-Answer System Using Large Language Models and Agents

Antony Seabra, Antony Seabra, Claudio Cavalcante, Claudio Cavalcante, João Nepomuceno, Lucas Lago, Nicolaas Ruberg, Sergio Lifschitz

2024

Abstract

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.

Paper Citation

in Harvard Style

Seabra A., Cavalcante C., Nepomuceno J., Lago L., Ruberg N. and Lifschitz S. (2024). Contrato360 2.0: A Document and Database-Driven Question-Answer System Using Large Language Models and Agents. In Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR; ISBN 978-989-758-716-0, SciTePress, pages 167-178. DOI: 10.5220/0013070400003838

in Bibtex Style

@conference{kdir24,
author={Antony Seabra and Claudio Cavalcante and João Nepomuceno and Lucas Lago and Nicolaas Ruberg and Sergio Lifschitz},
title={Contrato360 2.0: A Document and Database-Driven Question-Answer System Using Large Language Models and Agents},
booktitle={Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR},
year={2024},
pages={167-178},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013070400003838},
isbn={978-989-758-716-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR
TI - Contrato360 2.0: A Document and Database-Driven Question-Answer System Using Large Language Models and Agents
SN - 978-989-758-716-0
AU - Seabra A.
AU - Cavalcante C.
AU - Nepomuceno J.
AU - Lago L.
AU - Ruberg N.
AU - Lifschitz S.
PY - 2024
SP - 167
EP - 178
DO - 10.5220/0013070400003838
PB - SciTePress