Energy and Buildings, Год журнала: 2024, Номер unknown, С. 115162 - 115162
Опубликована: Дек. 1, 2024
Язык: Английский
Energy and Buildings, Год журнала: 2024, Номер unknown, С. 115162 - 115162
Опубликована: Дек. 1, 2024
Язык: Английский
Building Simulation, Год журнала: 2025, Номер unknown
Опубликована: Янв. 17, 2025
Язык: Английский
Процитировано
6Energy and Buildings, Год журнала: 2024, Номер 322, С. 114691 - 114691
Опубликована: Авг. 23, 2024
Язык: Английский
Процитировано
14Applied Energy, Год журнала: 2024, Номер 377, С. 124378 - 124378
Опубликована: Сен. 5, 2024
Язык: Английский
Процитировано
10Journal of Building Engineering, Год журнала: 2025, Номер unknown, С. 112356 - 112356
Опубликована: Март 1, 2025
Язык: Английский
Процитировано
0Engineering Construction & Architectural Management, Год журнала: 2025, Номер unknown
Опубликована: Апрель 30, 2025
Purpose Achieving smart question-answering (QA) for construction laws (CLs) holds significant promise in aiding domain professionals with legal inquiries. Existing studies of law (CLQA) rely on learning-based models, which require extensive training data and are limited to a narrow QA scope. Meanwhile, general-purpose large language models (GPLLMs) possess great potential CLQA but fall short domain-specific knowledge. This study aims propose data-driven expertise-based approach develop knowledge repository (CLKR) validate its effectiveness enhancing the performance GPLLMs. Design/methodology/approach methodology includes (1) recognizing 702 candidate CL documents from 374,992 official judgments, (2) building CLKR 387 filtered covering eight areas, (3) integrating seven representative GPLLMs (4) constructing 2,140-question dataset Professional Construction Engineer Qualification Examinations (PCEQEs) during 2014–2023 compare between pairs without CLKR. Findings The significantly enhances GPLLMs, yielding an impressive average accuracy increase 21.1%, individual improvements ranging 9.9 44.9%. Furthermore, boosts single-answer questions by 14.9% multiple-answer 38.3%. Additionally, enhancements across 8 areas 14.5 28.2%. Originality/value proposes developing external base empower expanding scope while bypassing complex traditional models. Moreover, this confirms augmenting GPLLM offers reusable test as benchmark.
Язык: Английский
Процитировано
0Artificial Intelligence Review, Год журнала: 2025, Номер 58(8)
Опубликована: Май 16, 2025
Abstract During the past decade, there has been rapid emergence, continuous development and advancements in field of Artificial Intelligence (AI), a broad adaptation ofLarge Language Models (LLMs) wide variety application domains transforming streamlining industry practices. However, construction yet to fully incorporate these technologies, delaying their wide-scale adaptation. Only limited number recent studies have explored opportunities, capabilities potential current LLM implementations domain Architecture Engineering Construction (AEC) industry, leaving significant gap this research. This study aims address provide an extensive review already established state-of-the-art applications use case scenarios LLMs AEC industry. Apart from that, by exploring key contributions limitations applications, considering relative reviews on subject, it was possible categorize them, extract emerging challenges future directions propose actionable recommendations for stakeholders. also includes introduction important concepts focusing transformer-based architectures providing list families.
Язык: Английский
Процитировано
0Applied Energy, Год журнала: 2025, Номер 393, С. 126169 - 126169
Опубликована: Май 20, 2025
Язык: Английский
Процитировано
0Applied Energy, Год журнала: 2024, Номер 380, С. 125059 - 125059
Опубликована: Дек. 13, 2024
Язык: Английский
Процитировано
2Journal of Artificial Intelligence and Soft Computing Research, Год журнала: 2024, Номер 15(2), С. 115 - 146
Опубликована: Дек. 1, 2024
Abstract The breakthrough in developing large language models (LLMs) over the past few years has led to their widespread implementation various areas of industry, business, and agriculture. aim this article is critically analyse generalise known results research directions on approaches development utilisation LLMs, with a particular focus functional characteristics when integrated into decision support systems (DSSs) for agricultural monitoring. subject integration LLMs DSSs agrotechnical main scientific applied are as follows: world experience using improve processes been analysed; critical analysis carried out, application architectures have identified; necessity focusing retrieval-augmented generation (RAG) an approach solving one limitations which limited knowledge base training data, established; prospects agriculture analysed highlight trustworthiness, explainability bias reduction priority research; potential socio-economic effect from RAG sector substantiated.
Язык: Английский
Процитировано
1Energy and Buildings, Год журнала: 2024, Номер unknown, С. 115162 - 115162
Опубликована: Дек. 1, 2024
Язык: Английский
Процитировано
0