arXiv cs.CL· Gunhee Cho, Hongyeob Kim, Yun-Gyung Cheong·· 15 小时前AI 评分27
FATE-5：面向大五人格连续可控的忠实特质表达对齐框架
FATE-5: Faithful Alignment of Trait Expression for Continuous Big Five Personality Control
AI 导读
FATE-5 是一个两阶段框架，将人格编码与自然度对齐分离，先用对话监督和辅助问卷目标学习大五人格画像的连续软提示表示，再通过基于对话质量与人格一致性的偏好对齐提升对话自然度。在三个语言模型骨干上，FATE-5 保持强特质表达的同时对话自然度显著高于其他强特质方法，在留出问卷上取得 0.97-0.99 的单调性相关和 8.9-12.4 的恢复 RMSE。
正文 · 原文
Abstract:Controlling personality in large language models is important for building conversational agents that can be customized to different users and interaction settings. However, existing personality control methods often face a tradeoff between strong trait expression and natural dialogue generation. We introduce FATE-5, Faithful Alignment of Trait Expression for the Big Five, a two-stage framework that separates personality encoding from naturalness alignment. FATE-5 first learns continuous soft prompt representations of Big Five profiles using dialogue supervision and an auxiliary survey objective. It then improves dialogue naturalness through preference alignment based on both dialogue quality and personality agreement. Across three language model backbones, FATE-5 maintains strong trait expression while achieving substantially higher dialogue naturalness than other trait-strong methods. On held-out questionnaires, it achieves monotonicity correlations of 0.97-0.99 and recovery RMSE of 8.9-12.4, substantially improving over the evaluated baselines. These results demonstrate effective continuous personality control while maintaining natural conversational behavior.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.34889 [cs.CL] |
| (or arXiv:2610.34889v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34889 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Gunhee Cho [view email]
[v1]
Mon, 26 Oct 2026 06:08:34 UTC (202 KB)
来源：arXiv cs.CL · arxiv.org