arXiv 2511.121302026-03-10cs.CL

观点PRISM：一种基于人设的多模态框架用于以用户为中心的对话立场检测

PRISM of Opinions: A Persona-Reasoned Multimodal Framework for User-centric Conversational Stance Detection

Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学（深圳））；Peng Cheng Laboratory, Shenzhen, China（鹏城实验室）；Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies（广东省新型安全智能技术重点实验室）；The Hong Kong Polytechnic University, Hong Kong, China（香港理工大学）；Macau University of Science and Technology, Hong Kong, China（澳门科学技术大学）

Bingbing Wang, Zhixin Bai, Zhengda Jin, Zihan Wang, Xintong Song, Jingjie Lin, Sixuan Li, Jing Li, Ruifeng Xu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

PRISM通过多模态和用户人设分析，提升对话立场检测的准确性与实用性。

摘要：

随着多模态社交媒体内容的迅速普及，多模态对话立场检测（MCSD）研究得以开展，旨在解读用户在复杂讨论中对特定目标的态度。然而，现有研究仍受限制于：1）伪多模态，即视觉线索仅出现在源帖子中，而评论被视为纯文本，这与现实中的多模态互动不一致；2）用户同质性，即不同用户被统一对待，忽视了塑造立场表达的个人特质。为了解决这些问题，我们引入了首个以用户为中心的MCSD数据集U-MStance，包含超过40,000条注释评论，涵盖六个现实世界目标。我们进一步提出PRISM，一种基于人设的多模态立场检测模型。PRISM首先从历史帖子和评论中推导出长期用户人设以捕捉个体特征，然后通过链式思考对话语境中的文本和视觉线索进行对齐，以弥合跨模态的语义和语用差距。最后，采用相互任务强化机制，共同优化立场检测和立场感知响应生成，以实现双向知识转移。在U-MStance上的实验表明，PRISM在强基线模型上取得了显著提升，证明了以用户为中心和基于情境的多模态推理在真实立场理解中的有效性。

英文摘要：

The rapid proliferation of multimodal social media content has driven research in Multimodal Conversational Stance Detection (MCSD), which aims to interpret users' attitudes toward specific targets within complex discussions. However, existing studies remain limited by: **1) pseudo-multimodality**, where visual cues appear only in source posts while comments are treated as text-only, misaligning with real-world multimodal interactions; and **2) user homogeneity**, where diverse users are treated uniformly, neglecting personal traits that shape stance expression. To address these issues, we introduce **U-MStance**, the first user-centric MCSD dataset, containing over 40k annotated comments across six real-world targets. We further propose **PRISM**, a **P**ersona-**R**easoned mult**I**modal **S**tance **M**odel for MCSD. PRISM first derives longitudinal user personas from historical posts and comments to capture individual traits, then aligns textual and visual cues within conversational context via Chain-of-Thought to bridge semantic and pragmatic gaps across modalities. Finally, a mutual task reinforcement mechanism is employed to jointly optimize stance detection and stance-aware response generation for bidirectional knowledge transfer. Experiments on U-MStance demonstrate that PRISM yields significant gains over strong baselines, underscoring the effectiveness of user-centric and context-grounded multimodal reasoning for realistic stance understanding.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。