PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media Disinformation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912810064150528 |
|---|---|
| author | Modzelewski, Arkadiusz Sosnowski, Witold Labruna, Tiziano Wierzbicki, Adam Martino, Giovanni Da San |
| author_facet | Modzelewski, Arkadiusz Sosnowski, Witold Labruna, Tiziano Wierzbicki, Adam Martino, Giovanni Da San |
| contents | Disinformation detection is a key aspect of media literacy. Psychological studies have shown that knowledge of persuasive fallacies helps individuals detect disinformation. Inspired by these findings, we experimented with large language models (LLMs) to test whether infusing persuasion knowledge enhances disinformation detection. As a result, we introduce the Persuasion-Augmented Chain of Thought (PCoT), a novel approach that leverages persuasion to improve disinformation detection in zero-shot classification. We extensively evaluate PCoT on online news and social media posts. Moreover, we publish two novel, up-to-date disinformation datasets: EUDisinfo and MultiDis. These datasets enable the evaluation of PCoT on content entirely unseen by the LLMs used in our experiments, as the content was published after the models' knowledge cutoffs. We show that, on average, PCoT outperforms competitive methods by 15% across five LLMs and five datasets. These findings highlight the value of persuasion in strengthening zero-shot disinformation detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_06842 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media Disinformation Modzelewski, Arkadiusz Sosnowski, Witold Labruna, Tiziano Wierzbicki, Adam Martino, Giovanni Da San Computation and Language Artificial Intelligence Disinformation detection is a key aspect of media literacy. Psychological studies have shown that knowledge of persuasive fallacies helps individuals detect disinformation. Inspired by these findings, we experimented with large language models (LLMs) to test whether infusing persuasion knowledge enhances disinformation detection. As a result, we introduce the Persuasion-Augmented Chain of Thought (PCoT), a novel approach that leverages persuasion to improve disinformation detection in zero-shot classification. We extensively evaluate PCoT on online news and social media posts. Moreover, we publish two novel, up-to-date disinformation datasets: EUDisinfo and MultiDis. These datasets enable the evaluation of PCoT on content entirely unseen by the LLMs used in our experiments, as the content was published after the models' knowledge cutoffs. We show that, on average, PCoT outperforms competitive methods by 15% across five LLMs and five datasets. These findings highlight the value of persuasion in strengthening zero-shot disinformation detection. |
| title | PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media Disinformation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2506.06842 |