WEKO3
アイテム
オンライン議論における言語モデルに基づくマルチエージェント事実検証システム
https://ipsj.ixsq.nii.ac.jp/records/235868
https://ipsj.ixsq.nii.ac.jp/records/235868f6301f68-12c6-4501-ad03-47ab8349dda1
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
IPSJ-Z86-7B-01.pdf (419.2 kB)
|
Copyright (c) 2024 by the Information Processing Society of Japan
|
| Item type | National Convention(1) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2024-03-01 | |||||||||
| タイトル | ||||||||||
| タイトル | オンライン議論における言語モデルに基づくマルチエージェント事実検証システム | |||||||||
| 言語 | ||||||||||
| 言語 | eng | |||||||||
| キーワード | ||||||||||
| 主題Scheme | Other | |||||||||
| 主題 | 人工知能と認知科学 | |||||||||
| 資源タイプ | ||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_5794 | |||||||||
| 資源タイプ | conference paper | |||||||||
| 著者所属 | ||||||||||
| 京大 | ||||||||||
| 著者所属 | ||||||||||
| 京大 | ||||||||||
| 著者名 |
董, 一涵
× 董, 一涵
× 伊藤, 孝行
|
|||||||||
| 論文抄録 | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | This paper presents the design and implementation of a multi-agent fact-checking system framework to judge how credible the posts are. Rumours and misinformation affect online discussions by misleading the directions of online discussions as they impact social networking services (SNS). Thus, detecting rumours and misinformation is still significant as it is within SNS fields.The previous research focusing on rumour detection has some issues: 1) Most of the fact-checking works are based on a single source which is assumed to be authoritative. 2) The judgement results made by large language models (LLM) with provided information were always seen as credible. 3) Binary label classification is not suitable for posts of online discussions since the participants may not spread rumours and misinformation intentionally. To address the obstacles and challenges mentioned above, a multi-agent fact-checking system framework connected with LLM is conducted to verify if posts of online discussions are trustworthy.Specifically, to address issues 1) and 2), multiple fact-checking agents are designed and implemented in this system framework, and each agent gains evidence from a unique information source to judge the credibility of claims with their confidence. For issue 3), a mechanism to calculate the credibility of posts with the judgement results and confidence of agents, and to classify the original posts using multiple labels, is also designed.Finally, the system was tested using a few related data sets. The results of the test are also included in this paper to illustrate that the system framework is completely feasible and practical. | |||||||||
| 書誌レコードID | ||||||||||
| 収録物識別子タイプ | NCID | |||||||||
| 収録物識別子 | AN00349328 | |||||||||
| 書誌情報 |
第86回全国大会講演論文集 巻 2024, 号 1, p. 41-42, 発行日 2024-03-01 |
|||||||||
| 出版者 | ||||||||||
| 言語 | ja | |||||||||
| 出版者 | 情報処理学会 | |||||||||
