LLM Agent for Disinformation Detection Based on DISARM Framework | Publication

Title	LLM Agent for Disinformation Detection Based on DISARM Framework
Creator	沈錳坤 Shan, Man-Kwan;Tseng, Kevin
Contributor	資訊系
Date	2024-06
Date Issued	2025-01-23
Summary	The rise of AI-generated disinformation driven by large language models (LLMs) exacerbates threats to information trust and democracy. Motivated by the need for efficient detection, this paper integrates the DISARM framework with LLMs to enhance capabilities. The proposed OSINT LLM Agent leverages DISARM's structure and LLMs' reasoning for an effective, adaptable solution against disinformation campaigns. Experiments using real-world cases demonstrate feasibility and effectiveness, highlighting DISARM-LLM integration's potential for advanced detection.
Relation	International AAAI Conference on Web and Social Media Workshop: Digital State Sponsored Disinformation and Propaganda, AAAI
Type	conference
DOI	https://doi.org/10.36190/2024.68

dc.contributor	資訊系
dc.creator (作者)	沈錳坤
dc.creator (作者)	Shan, Man-Kwan;Tseng, Kevin
dc.date (日期)	2024-06
dc.date.accessioned	2025-01-23	-
dc.date.available	2025-01-23	-
dc.date.issued (上傳時間)	2025-01-23	-
dc.identifier.uri (URI)	https://nccur.lib.nccu.edu.tw/handle/140.119/155307	-
dc.description.abstract (摘要)	The rise of AI-generated disinformation driven by large language models (LLMs) exacerbates threats to information trust and democracy. Motivated by the need for efficient detection, this paper integrates the DISARM framework with LLMs to enhance capabilities. The proposed OSINT LLM Agent leverages DISARM's structure and LLMs' reasoning for an effective, adaptable solution against disinformation campaigns. Experiments using real-world cases demonstrate feasibility and effectiveness, highlighting DISARM-LLM integration's potential for advanced detection.
dc.format.extent	529776 bytes	-
dc.format.mimetype	application/pdf	-
dc.relation (關聯)	International AAAI Conference on Web and Social Media Workshop: Digital State Sponsored Disinformation and Propaganda, AAAI
dc.title (題名)	LLM Agent for Disinformation Detection Based on DISARM Framework
dc.type (資料類型)	conference
dc.identifier.doi (DOI)	10.36190/2024.68
dc.doi.uri (DOI)	https://doi.org/10.36190/2024.68