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

IF 9.6 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction Pub Date : 2024-12-04 DOI:10.1016/j.autcon.2024.105891

Chi-Yun Liu, Jui-Sheng Chou

{"title":"Automated legal consulting in construction procurement using metaheuristically optimized large language models","authors":"Chi-Yun Liu, Jui-Sheng Chou","doi":"10.1016/j.autcon.2024.105891","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"18 1","pages":""},"PeriodicalIF":9.6000,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Automation in Construction","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1016/j.autcon.2024.105891","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

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.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Automation in Construction 工程技术-工程：土木

CiteScore

19.20

自引率

16.50%

发文量

563

审稿时长

8.5 months

期刊介绍： Automation in Construction is an international journal that focuses on publishing original research papers related to the use of Information Technologies in various aspects of the construction industry. The journal covers topics such as design, engineering, construction technologies, and the maintenance and management of constructed facilities. The scope of Automation in Construction is extensive and covers all stages of the construction life cycle. This includes initial planning and design, construction of the facility, operation and maintenance, as well as the eventual dismantling and recycling of buildings and engineering structures.