从用户行为日志中挖掘多角色人格，让生成的人格更真实可信。
Hierarchical Multi-Persona Induction from User Behavioral Logs: Learning Evidence-Grounded and Truthful Personas
- 分层聚合行为数据为意图记忆，再聚类生成人格。
- 在三个数据集上提升人格一致性与真实性，预测未来交互更准。
- 适合做个性化推荐、智能客服的团队使用。
行为日志蕴含丰富的用户建模信号，但噪声多且意图混杂。现有方法利用大模型从日志生成自然语言人格，但评估常侧重下游任务表现，难以保证人格本身质量。本文提出一种分层框架，将用户行为聚合为意图记忆，通过聚类与标注生成多个基于证据的人格。将人格生成建模为优化问题，目标函数涵盖簇内凝聚度、人格与证据对齐度及真实性。采用组级扩展的直接偏好优化（DPO）训练模型。在大规模服务日志及两个公开数据集上的实验表明，该方法生成的人格更具连贯性、证据支撑性与可信度，并提升了未来交互预测性能。
原文摘要 · Abstract (English)
Behavioral logs provide rich signals for user modeling, but are noisy and interleaved across diverse intents. Recent work uses LLMs to generate interpretable natural-language personas from user logs, yet evaluation often emphasizes downstream utility, providing limited assurance of persona quality itself. We propose a hierarchical framework that aggregates user actions into intent memories and induces multiple evidence-grounded personas by clustering and labeling these memories. We formulate persona induction as an optimization problem over persona quality-captured by cluster cohesion, persona-evidence alignment, and persona truthfulness-and train the persona model using a groupwise extension of Direct Preference Optimization (DPO). Experiments on a large-scale service log and two public datasets show that our method induces more coherent, evidence-grounded, and trustworthy personas, while also improving future interaction prediction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。