近日，CIKM 2024会议公布了论文录用结果，硕士生乔雪宁关于大模型对话恶意性检测的研究成果被录取为短文，CIKM是信息检索领域顶级会议，被CCF推荐为B类国际学术会议。

题目：MPHDetect: Multi-View Prompting and Hypergraph Fusion for Malevolence Detection in Dialogues

Abstract: Malevolence detection in dialogues aims to identify harmful or inappropriate utterances, significantly impacting dialogue quality and user satisfaction. Although existing studies have shown promising performance by modeling interaction patterns from dialogue history, various malevolence-invoking factors, such as fine-grained emotions, evolving topics, and user profiles, are often overlooked. To comprehensively consider these factors, we propose a hypergraph fusion model by employing multi-view LLM-driven prompts for malevolence detection in dialogues. Our model integrates emotion context, topic context, user profile context, and interaction context, utilizing hypergraphs to establish high-order contextual relationships from multi views for deducing malevolence-invoking semantics. Experimental results on two benchmark datasets demonstrate that our model achieves state-of-the-art performance.

中文摘要：对话恶意检测旨在识别有害或不适当的言论，这对对话质量和用户满意度有着重大影响。尽管现有研究通过建模对话历史中的交互模式取得了客观的性能，但通常忽视了许多引发恶意的因素，例如细粒度情绪、不断演变的话题和用户画像。为了全面考虑这些因素，我们提出了一种通过使用多视角的大语言模型驱动提示的超图融合模型，用于对话中的恶意检测。我们的模型整合了情绪上下文、话题上下文、用户画像上下文和交互上下文，利用超图从多视角建立高阶上下文关系，以推导恶意引发的语义。在两个基准数据集上的实验结果表明，我们的模型达到了最先进的性能。