打造能帮人看清自我的对话助手，而非只缓解情绪。
Ekova: A Personality-Support Agent for Self-Discovery Dialogue
- 构建中文自我发现对话数据集DSD，含8590条真实对话。
- 提出OrthoTune框架，使模型在多项指标上提升16.3%。
- 开发持久化人格支持助手Ekova，支持跨会话记忆与个性化选择。
情感支持系统长期聚焦于即时缓解用户情绪困扰。我们提出一种互补需求：帮助用户更清晰地认识自我，形成名为‘人格支持’（Personality Support, PS）的新范式。PS非心理咨询或临床干预，而是聚焦认知清晰度与自我表达，而非症状缓解或诊断。我们从三个层面实现该范式：首先，构建包含8,590个样本的中文自我发现对话数据集DSD，通过五种最小交互单元（Coach、Warm、Tsukkomi、Real、Gonzo）的真实纵向对话收集；其次，设计DeepSupport多人格支持系统，采用专为PS优化的OrthoTune框架，结合风格适配器与风格一致性正则化；第三，将五个DeepSupport人格整合为Ekova，一个具备统一跨会话记忆层的持久人格支持代理，支持自适应路由与用户定制人格选择。实验表明，OrthoTune训练模型在所有指标上相比最强提示基线平均提升16.3%。代码已开源。
原文摘要 · Abstract (English)
Emotional Support (ES) systems have long optimized a single objective: alleviating the user's emotional distress in the moment. We argue that a complementary need, helping users see themselves more clearly, defines a distinct paradigm we call Personality Support (PS). PS is not counseling or clinical intervention: it targets cognitive clarity and self-articulation, not symptom relief or diagnosis. We instantiate this paradigm in three layers. First, we present DSD, a Chinese self-discovery PS Dataset of 8,590 samples collected through real longitudinal interaction across five minimal units, Coach, Warm, Tsukkomi, Real, and Gonzo. Second, we build DeepSupport, a multi-persona PS system trained with OrthoTune, a PS-tailored framework with style-specific adapters and a style-consistency regularizer. Third, we unify the five DeepSupport personas into Ekova, a persistent personality-support agent with a unified cross-session memory layer, supporting both adaptive routing and user-customized persona selection. Experiments show that OrthoTune-trained models outperform all baselines with an average relative gain of 16.3% across all metrics over the strongest prompt-based baseline. Code is available at https://github.com/Yukyin/Ekova.
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。