Verification and Consideration for Utilization of Large Language Models in Civil Engineering
-
- SUGETA Daisuke
- 日本工営株式会社 中央研究所
-
- HAKOISHI Kenta
- 日本工営株式会社 中央研究所
-
- HITOKOTO Masayuki
- 日本工営株式会社 中央研究所
Bibliographic Information
- Other Title
-
- 土木・建設分野における大規模言語モデルの利活用に向けた検証と考察
Abstract
<p>In this study, we verified the accuracy of large language models (ChatGPT) using a database system containing texts in the field of civil engineering. As a result, we confirmed the effectiveness of a extraction task of similar technologies and dialogue task based on the database system operation rules within the validated range. We also confirmed the superiority of prompts based on few-shot-learning in the task of categorizing new technology information. In addition, we confirmed the superiority of prompts created using only job descriptions as personas in the same task.</p>
Journal
-
- Artificial Intelligence and Data Science
-
Artificial Intelligence and Data Science 4 (3), 670-676, 2023
Japan Society of Civil Engineers
- Tweet
Details 詳細情報について
-
- CRID
- 1390298124265614720
-
- ISSN
- 24359262
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
-
- Abstract License Flag
- Disallowed