Automated legal consulting in construction procurement using metaheuristically optimized large language models,Automation in Construction

当前位置： X-MOL 学术 › Autom. Constr. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Automated legal consulting in construction procurement using metaheuristically optimized large language models
Automation in Construction ( IF 9.6 ) Pub Date : 2024-12-04 , DOI: 10.1016/j.autcon.2024.105891
Chi-Yun Liu, Jui-Sheng Chou

This paper introduces a hybrid optimization algorithm, Pilgrimage Walk Optimization - Differential Evolution (PWO-DE), inspired by Taiwan's cultural traditions, to fine-tune large language models (LLMs) for government procurement legal consulting. Addressing the unique requirements of Traditional Chinese, this research develops two tailored LLMs, Llama3-TAIDE and Taiwan-LLM, which significantly enhance automated legal advisory systems. Through rigorous comparative evaluations, the PWO-DE algorithm demonstrates superior performance against various well-established single and hybrid metaheuristic algorithms, ensuring effective decision-making and risk management in government procurement. A user-friendly chat interface has also been created, facilitating the practical application of LLMs, increasing their accessibility and impact on legal consulting within the construction and legal fields. This study showcases the integration of cultural insights into algorithmic design, establishing a new benchmark for future advancements in the automation of complex legal consulting tasks.

更新日期：2024-12-04

点击分享查看原文

点击收藏

阅读更多本刊新发论文本刊介绍/投稿指南