利用大模型幻觉生成反向推理，提升假新闻检测能力
Is LLMs Hallucination Usable? LLM-based Negative Reasoning for Fake News Detection
- 通过大模型反思生成合理与错误推理对
- 在三个数据集上显著优于基线方法
- 适合关注模型可解释性与抗欺骗的从业者
由知识幻觉导致的不可靠回应可能使大模型在决策中表现不稳定。然而，尚未有研究探讨大模型幻觉是否可用于生成反向推理以辅助假新闻检测。本文提出一种新型监督自强化推理修正方法SR$^3$，通过大模型反思生成新闻的合理推理与错误理解（负向推理）。在此基础上，构建基于负向推理的新闻学习模型NRFE，利用正负推理对学习语义一致性。为避免标签诱导推理影响，引入仅以新闻内容为输入的学生模型NRFE-D，通过知识蒸馏评估方法性能。在三个主流假新闻数据集上的实验结果表明，该方法在三类基线（提示工程、预训练小模型微调及其他典型假新闻检测方法）中均表现更优。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。