GAIus: Combining Genai with Legal Clauses Retrieval for Knowledge-Based Assistant

Michał Matak, Jarosław A. Chudziak

2025

Abstract

In this paper we discuss the capability of large language models to base their answer and provide proper ref-erences when dealing with legal matters of non-english and non-chinese speaking country. We discuss the history of legal information retrieval, the difference between case law and statute law, its impact on the legal tasks and analyze the latest research in this field. Basing on that background we introduce gAIus, the architecture of the cognitive LLM-based agent, whose responses are based on the knowledge retrieved from certain legal act, which is Polish Civil Code. We propose a retrieval mechanism which is more explainable, human-friendly and achieves better results than embedding-based approaches. To evaluate our method we create special dataset based on single-choice questions from entrance exams for law apprenticeships conducted in Poland. The proposed architecture critically leveraged the abilities of used large language models, improving the gpt-3.5-turbo-0125 by 419%, allowing it to beat gpt-4o and lifting gpt-4o-mini score from 31% to 86%. At the end of our paper we show the possible future path of research and potential applications of our findings.

Paper Citation

in Harvard Style

Matak M. and Chudziak J. (2025). GAIus: Combining Genai with Legal Clauses Retrieval for Knowledge-Based Assistant. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 868-875. DOI: 10.5220/0013191800003890

in Bibtex Style

@conference{icaart25,
author={Michał Matak and Jarosław Chudziak},
title={GAIus: Combining Genai with Legal Clauses Retrieval for Knowledge-Based Assistant},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2025},
pages={868-875},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013191800003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - GAIus: Combining Genai with Legal Clauses Retrieval for Knowledge-Based Assistant
SN - 978-989-758-737-5
AU - Matak M.
AU - Chudziak J.
PY - 2025
SP - 868
EP - 875
DO - 10.5220/0013191800003890
PB - SciTePress