近日，IJCAI 2025公布了录用论文列表，实验室两篇长文被录用。IJCAI是人工智能领域的国际顶级会议，在CCF推荐列表中认定为A类学术会议。

录用论文1：Unveiling Maternity and Infant Care Conversations: A Chinese Dialogue Dataset for Enhanced Parenting Support

作者：硕士生王俊龙、乔雪宁、于迩晨，徐博老师等

合作机构：美柚网

摘要：The rapid development of large language models has greatly advanced human-computer dialogue research. However, applying these models to specialized fields like maternity and infant care often leads to subpar performance due to a lack of domain-specific datasets. To address this problem, we have created MicDialogue, a Chinese dialogue dataset for maternity and infant care. MicDialogue involves a wide range of specialized topics, including gynecological health, pediatric care, pregnancy preparation, and emotional counseling. This dataset is curated from two types of Chinese social media: short videos and blog posts. Short videos capture real-time interactions and pragmatic dialogue patterns, while blog posts offer comprehensive coverage of various topics within the domain. We have also included detailed annotations for topics, diseases, symptoms, and causes, enabling in-depth research. Additionally, we developed a knowledge-driven benchmark model using LLM-based prompt learning and multiple knowledge graphs to address diverse dialogue topics. Experiments validate MicDialogue's usability, providing benchmarks for future research and essential data for fine-tuning language models in maternity and infant care.

大型语言模型的迅速发展极大地推动了人机对话研究的进步。然而，在孕产育儿等专业领域中应用这些模型时，往往因缺乏领域特定的数据集而表现不佳。为了解决这一问题，我们构建了 MicDialogue，一个面向孕产育儿领域的中文对话数据集。MicDialogue 涉及广泛的专业话题，包括妇科健康、儿童护理、备孕指导以及情绪疏导等内容。该数据集来源于两类中文社交媒体平台：短视频与博客。短视频反映了实时互动和实用的对话模式，而博客内容则对相关领域的各类主题进行了全面覆盖。我们还为数据集提供了详细的标注信息，包括话题、疾病、症状及其成因，便于进行深入研究。此外，我们设计了一个基于大型语言模型的提示学习方法，并结合多个知识图谱构建了一个知识驱动的基准模型，用于应对多样化的对话主题。实验结果验证了 MicDialogue 的可用性，不仅为后续研究提供了评估基准，也为语言模型在孕产育儿领域的微调提供了重要数据支持。

录用论文2：SpeechHGT: A Multimodal Hypergraph Transformer for Speech-Based Early Alzheimer’s Disease Detection

作者：博士生Shagufta Abid、Ahsan Shehzad，张冬瑜老师等

摘要：Early detection of Alzheimer’s disease (AD) through spontaneous speech analysis represents a promising, non-invasive diagnostic approach. Existing methods predominantly rely on fusion-based multimodal deep learning, effectively integrating linguistic and acoustic features. However, these methods inadequately model higher-order interactions between modalities, reducing diagnostic accuracy. To address this, we introduce SpeechHGT, a multimodal hypergraph transformer designed to capture and learn higher-order interactions in spontaneous speech features. SpeechHGT encodes multimodal features as hypergraphs, where nodes represent individual features and hyperedges represent grouped interactions. A novel hypergraph attention mechanism enables robust modeling of both pairwise and higher-order interactions. Experimental evaluations on the DementiaBank datasets reveal that SpeechHGT achieves state-of-the-art performance, surpassing baseline models in accuracy and F1 score. These results highlight the potential of hypergraph-based models to improve AI-driven diagnostic tools for early AD detection.

通过自发语音分析实现阿尔茨海默病（AD）的早期检测是一种极具前景的非侵入式诊断方法。现有方法主要依赖基于融合的多模态深度学习，能有效整合语言与声学特征。然而这些方法对模态间高阶交互的建模不足，导致诊断准确性降低。为此，我们提出SpeechHGT——一种多模态超图变压器模型，专门用于捕捉和学习自发语音特征中的高阶交互关系。该模型将多模态特征编码为超图结构，其中节点代表独立特征，超边表征分组交互关系。创新的超图注意力机制实现了对成对交互和高阶交互的鲁棒建模。在DementiaBank数据集上的实验表明，SpeechHGT以超越基线模型的准确率和F1分数达到当前最优性能。这些成果彰显了超图模型在改进AI驱动型早期AD诊断工具方面的潜力。