报告时间：2025年6月23日（星期一）09:00-11:30
报告地点：合肥工业大学管理学院925会议室
报告人：Yi Yang 杨毅
工作单位：香港科技大学 Hong Kong University of Science and Technology
举办单位：合肥工业大学管理学院
报告简介：
Recent advancements in Large Language Models (LLMs) demonstrate remarkable capabilities across various fields. These developments lead to more direct communication between humans and LLMs in various situations, such as social companionship and psychological support. However, LLMs often exhibit limitations in emotional perception and social competence during real-world conversations. These limitations partly originate from their inability to adapt their communication style and emotional expression to different social contexts. While existing approaches attempt to address these limitations through prompting engineering or specialized fine-tuning, these methods still face challenges in maintaining general capabilities. To address this issue, we introduce PersonaFuse, a novel framework that enables LLMs to adapt and express different personalities for varying situations. Inspired by Trait Activation Theory and the Big Five personality model, PersonaFuse employs a situation-aware architecture that combines persona adapters with a dynamic routing network, enabling contextual trait expression while preserving the model's capabilities and safety guardrails. Experimental results demonstrate that PersonaFuse significantly outperforms baseline models across multiple dimensions, achieving up to 69% improvement in emotional intelligence tasks and a 12% gain in social cognition tasks while maintaining model safety and general task performance. Furthermore, PersonaFuse also shows improved performance in downstream applications that involve humans in interactions, including mental health support and review-based Q&A for e-commerce. These findings demonstrate that PersonaFuse offers a theoretically grounded and practical approach for developing social-emotional enhanced LLMs, marking a significant advancement toward more human-centric AI systems.
报告人简介：
Yi Yang is an Associate Professor and Lee Heng Fellow in the Department of Information Systems, Business Statistics and Operations Management at the Hong Kong University of Science and Technology (HKUST). He is also the Director of the Center for Business and Social Analytics (CBSA).
He received his Ph.D. in Computer Science from Northwestern University. His research focuses on designing machine learning methods to tackle complex challenges in business and FinTech. His work has appeared in leading journals in the business domain, including Information Systems Research, Management Information Systems Quarterly, Journal of Marketing, Contemporary Accounting Research, and INFORMS Journal on Computing. He has also published in premier venues in machine learning and natural language processing, such as ACL, EMNLP, KDD, ICLR, TKDE, and TOIS.
Professor Yang serves as an Associate Editor for the INFORMS Journal on Computing and the MIS Quarterly Special Issue on “The Institutional Press in the Digital Age.” He is also a member of the Editorial Review Board of Information Systems Research. He is also a Senior Area Chair for the ACL Rolling Review (ARR).
His research on AI and finance has had significant industry impact. His work has been referenced in policy statements by the Hong Kong Government and endorsed by the Hong Kong Monetary Authority (HKMA). He is currently leading research collaborations with Ping An Insurance, HSBC, WeBank, and HKMA.
