Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.11078 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915340563251200 |
|---|---|
| author | Yang, Yuzhou Zhou, Yangming Zhu, Zhiying Qian, Zhenxing Zhang, Xinpeng Li, Sheng |
| author_facet | Yang, Yuzhou Zhou, Yangming Zhu, Zhiying Qian, Zhenxing Zhang, Xinpeng Li, Sheng |
| contents | The proliferation of deceptive content online necessitates robust Fake News Detection (FND) systems. While evidence-based approaches leverage external knowledge to verify claims, existing methods face critical limitations: noisy evidence selection, generalization bottlenecks, and unclear decision-making processes. Recent efforts to harness Large Language Models (LLMs) for FND introduce new challenges, including hallucinated rationales and conclusion bias. To address these issues, we propose \textbf{RoE-FND} (\textbf{\underline{R}}eason \textbf{\underline{o}}n \textbf{\underline{E}}xperiences FND), a framework that reframes evidence-based FND as a logical deduction task by synergizing LLMs with experiential learning. RoE-FND encompasses two stages: (1) \textit{self-reflective knowledge building}, where a knowledge base is curated by analyzing past reasoning errors, namely the exploration stage, and (2) \textit{dynamic criterion retrieval}, which synthesizes task-specific reasoning guidelines from historical cases as experiences during deployment. It further cross-checks rationales against internal experience through a devised dual-channel procedure. Key contributions include: a case-based reasoning framework for FND that addresses multiple existing challenges, a training-free approach enabling adaptation to evolving situations, and empirical validation of the framework's superior generalization and effectiveness over state-of-the-art methods across three datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_11078 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RoE-FND: A Case-Based Reasoning Approach with Dual Verification for Fake News Detection via LLMs Yang, Yuzhou Zhou, Yangming Zhu, Zhiying Qian, Zhenxing Zhang, Xinpeng Li, Sheng Computation and Language The proliferation of deceptive content online necessitates robust Fake News Detection (FND) systems. While evidence-based approaches leverage external knowledge to verify claims, existing methods face critical limitations: noisy evidence selection, generalization bottlenecks, and unclear decision-making processes. Recent efforts to harness Large Language Models (LLMs) for FND introduce new challenges, including hallucinated rationales and conclusion bias. To address these issues, we propose \textbf{RoE-FND} (\textbf{\underline{R}}eason \textbf{\underline{o}}n \textbf{\underline{E}}xperiences FND), a framework that reframes evidence-based FND as a logical deduction task by synergizing LLMs with experiential learning. RoE-FND encompasses two stages: (1) \textit{self-reflective knowledge building}, where a knowledge base is curated by analyzing past reasoning errors, namely the exploration stage, and (2) \textit{dynamic criterion retrieval}, which synthesizes task-specific reasoning guidelines from historical cases as experiences during deployment. It further cross-checks rationales against internal experience through a devised dual-channel procedure. Key contributions include: a case-based reasoning framework for FND that addresses multiple existing challenges, a training-free approach enabling adaptation to evolving situations, and empirical validation of the framework's superior generalization and effectiveness over state-of-the-art methods across three datasets. |
| title | RoE-FND: A Case-Based Reasoning Approach with Dual Verification for Fake News Detection via LLMs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.11078 |