高级检索
    柯婧, 谢哲勇, 徐童, 陈宇豪, 廖祥文, 陈恩红. 基于大模型隐含语义增强的细粒度虚假新闻检测方法[J]. 计算机研究与发展. DOI: 10.7544/issn1000-1239.202330967
    引用本文: 柯婧, 谢哲勇, 徐童, 陈宇豪, 廖祥文, 陈恩红. 基于大模型隐含语义增强的细粒度虚假新闻检测方法[J]. 计算机研究与发展. DOI: 10.7544/issn1000-1239.202330967
    Ke Jing, Xie Zheyong, Xu Tong, Chen Yuhao, Liao Xiangwen, Chen Enhong. An Implicit Semantic Enhancement Fine-Grained Fake News Detection Method Based on Large Language Model[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202330967
    Citation: Ke Jing, Xie Zheyong, Xu Tong, Chen Yuhao, Liao Xiangwen, Chen Enhong. An Implicit Semantic Enhancement Fine-Grained Fake News Detection Method Based on Large Language Model[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202330967

    基于大模型隐含语义增强的细粒度虚假新闻检测方法

    An Implicit Semantic Enhancement Fine-Grained Fake News Detection Method Based on Large Language Model

    • 摘要: 随着生成式人工智能技术的发展,许多领域都得到了帮助与发展,但与此同时虚假信息的构建与传播变得更加简单,虚假信息的检测也随之难度增加. 先前的工作主要聚焦于语法问题,内容煽动性等方面的特点,利用深度学习模型对虚假新闻内容进行建模. 这样的方式不仅缺乏对内容本身的判断,还无法回溯模型的判别原因. 针对上述问题提出一种基于大模型隐含语义增强的细粒度虚假新闻检测方法. 该方法充分挖掘并利用了现有的生成式大语言模型所具有的总结与推理能力,按照主干事件、细粒度次要事件和隐含信息推理的顺序进行层级式推导,逐步判别新闻的真实性. 通过分解任务的方式,该方法最大程度发挥了模型的能力,提高了对虚假新闻的捕获能力,同时该方法也具有一定的可解释性,能够为检测提供判别依据.

       

      Abstract: The advancement of generative artificial intelligence technology has significantly contributed to the progress in various fields. However, this technological development has also inadvertently facilitated the creation and widespread dissemination of misinformation. Prior research has concentrated on addressing grammatical issues, inflammatory content, and other pertinent features by employing deep learning models to characterize and model deceptive elements within fake news content. These approaches not only lack the capability to assess the content itself but also fall short in elucidating the reasons behind the model's classification. Based on the above problems, this paper proposes a fine-grained fake news detection method with implicit semantic enhancement. This method fully utilizes the summarization and reasoning capabilities of the existing generative large language model. It employs inference based on major events, fine-grained minor events, and implicit information to systematically evaluate the authenticity of news content. This method strategically leverages the full potential of the model by decomposing tasks, thereby not only optimizing its proficiency but also significantly enhancing its prowess in capturing instances of fake news. Simultaneously, it is designed to be interpretable, providing a solid foundation for detection. With its inherent ability, this method not only ensures reliable identification but also holds vast potential for diverse applications.

       

    /

    返回文章
    返回