Effectiveness of Security Export Control Ontology for Predicting Answer Type and Regulation Categories

Rzepka, Rafal; Obayashi, Akihiko

Proceedings of the 2024 8th International Conference on Advances in Artificial Intelligence, 2025, 156-161

Permalink : https://hdl.handle.net/2115/95947

このアイテムのアクセス数:99件（2026-08-18 18:04 集計）

閲覧可能ファイル 

ファイル フォーマット サイズ 閲覧回数 説明
ICAAI2024 156 - 161 pdf 1.29 MB 105

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

アクセス権
open access
URI
https://hdl.handle.net/2115/95947
タイトル
Effectiveness of Security Export Control Ontology for Predicting Answer Type and Regulation Categories
著者
e-Rad_Researcher
80396316
著者名
Rzepka, Rafal
著者名
Obayashi, Akihiko
言語
英語
キーワード
Expert Systems
GraphRAG
Large Language Models
Knowledge Graph
Security Export Control
発行日
2025-03-03
出版者
ACM
収録物名
Proceedings of the 2024 8th International Conference on Advances in Artificial Intelligence
ページ
156-161
記述
ICAAI 2024: 2024 The 8th International Conference on Advances in Artificial Intelligence London United Kingdom October 17 - 19, 2024
抄録
In this paper we present results of our experiments investigating if an expert knowledge graph can improve Large Language Models accuracy in predicting correct answer labels and regulations related to the topic of security export control. As the lack of related data prevents machine-learning or fine-tuning approaches, we implement prompt expansion by searching most relevant nodes of the graph and adding the expanded context to the prompt. Results of our experiments show that the addition improved answer type selection but clearly hamper the capability of finding a correct regulation category.
会議記述
会議名
2024 The 8th International Conference on Advances in Artificial Intelligence
開催地
London
開催国
United Kingdom of Great Britain and Northern Ireland
資源タイプ
会議発表論文
出版タイプ
Accepted Manuscript
権利情報
Creative Commons Attribution 4.0 International
関連情報 (isVersionOf)
出版社版DOI
https://doi.org/10.1145/3704137.3704180