作者位次 #2/11ACL 2026Poster· Natural Language Processing
When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents
Jiahe Guo · Xiangran Guo · Yulin Hu · Zimo Long · Xingyu Sui · Xuda Zhi · Yongbo Huang · Hao He · Weixiang Zhao · Yanyan Zhao · Bing Qin
摘要
Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions.However, most work on personalized agents prioritizes utility and user experience, treating memory as a neutral component and largely overlooking its safety implications.In this paper, we...