In this section
@inproceedings{Nguyen:2023:10.3233/faia230991,
author = {Nguyen, HT and Goebel, R and Toni, F and Stathis, K and Satoh, K},
doi = {10.3233/faia230991},
pages = {371--374},
publisher = {IOS Press},
title = {LawGiBa – Combining GPT, knowledge bases, and logic programming in a legal assistance system},
url = {http://dx.doi.org/10.3233/faia230991},
year = {2023}
}
TY - CPAPER
AB - We present LawGiBa, a proof-of-concept demonstration system for legal assistance that combines GPT, legal knowledge bases, and Prolog’s logic programming structure to provide explanations for legal queries. This novel combination effectively and feasibly addresses the hallucination issue of large language models (LLMs) in critical domains, such as law. Through this system, we demonstrate how incorporating a legal knowledge base and logical reasoning can enhance the accuracy and reliability of legal advice provided by AI models like GPT. Though our work is primarily a demonstration, it provides a framework to explore how knowledge bases and logic programming structures can be further integrated with generative AI systems, to achieve improved results across various natural languages and legal systems.
AU - Nguyen,HT
AU - Goebel,R
AU - Toni,F
AU - Stathis,K
AU - Satoh,K
DO - 10.3233/faia230991
EP - 374
PB - IOS Press
PY - 2023///
SN - 0922-6389
SP - 371
TI - LawGiBa – Combining GPT, knowledge bases, and logic programming in a legal assistance system
UR - http://dx.doi.org/10.3233/faia230991
UR - http://hdl.handle.net/10044/1/109811
ER -