Is LLMs Hallucination Usable? LLM-based Negative Reasoning for Fake News Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915194379173888 |
|---|---|
| author | Zhang, Chaowei Feng, Zongling Zhang, Zewei Qiang, Jipeng Xu, Guandong Li, Yun |
| author_facet | Zhang, Chaowei Feng, Zongling Zhang, Zewei Qiang, Jipeng Xu, Guandong Li, Yun |
| contents | The questionable responses caused by knowledge hallucination may lead to LLMs' unstable ability in decision-making. However, it has never been investigated whether the LLMs' hallucination is possibly usable to generate negative reasoning for facilitating the detection of fake news. This study proposes a novel supervised self-reinforced reasoning rectification approach - SR$^3$ that yields both common reasonable reasoning and wrong understandings (negative reasoning) for news via LLMs reflection for semantic consistency learning. Upon that, we construct a negative reasoning-based news learning model called - \emph{NRFE}, which leverages positive or negative news-reasoning pairs for learning the semantic consistency between them. To avoid the impact of label-implicated reasoning, we deploy a student model - \emph{NRFE-D} that only takes news content as input to inspect the performance of our method by distilling the knowledge from \emph{NRFE}. The experimental results verified on three popular fake news datasets demonstrate the superiority of our method compared with three kinds of baselines including prompting on LLMs, fine-tuning on pre-trained SLMs, and other representative fake news detection methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_09153 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Is LLMs Hallucination Usable? LLM-based Negative Reasoning for Fake News Detection Zhang, Chaowei Feng, Zongling Zhang, Zewei Qiang, Jipeng Xu, Guandong Li, Yun Computation and Language Artificial Intelligence The questionable responses caused by knowledge hallucination may lead to LLMs' unstable ability in decision-making. However, it has never been investigated whether the LLMs' hallucination is possibly usable to generate negative reasoning for facilitating the detection of fake news. This study proposes a novel supervised self-reinforced reasoning rectification approach - SR$^3$ that yields both common reasonable reasoning and wrong understandings (negative reasoning) for news via LLMs reflection for semantic consistency learning. Upon that, we construct a negative reasoning-based news learning model called - \emph{NRFE}, which leverages positive or negative news-reasoning pairs for learning the semantic consistency between them. To avoid the impact of label-implicated reasoning, we deploy a student model - \emph{NRFE-D} that only takes news content as input to inspect the performance of our method by distilling the knowledge from \emph{NRFE}. The experimental results verified on three popular fake news datasets demonstrate the superiority of our method compared with three kinds of baselines including prompting on LLMs, fine-tuning on pre-trained SLMs, and other representative fake news detection methods. |
| title | Is LLMs Hallucination Usable? LLM-based Negative Reasoning for Fake News Detection |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.09153 |