arXiv cs.CL· Chaogui Gou·· 12 小时前AI 评分31
Psy-Chronicle：基于学生学期时间线合成校园心理咨询对话
Psy-Chronicle: Synthesizing Campus Counseling Grounded in a Student's Semester Timeline
AI 导读
Psy-Chronicle 是一个事件驱动的多轮心理咨询合成框架，将模拟学生的一学期压力事件图谱与跨会话记忆结合，生成沿时间线推进的咨询对话。基于该框架构建的 CPCD 是开放中文数据集，包含 100 名学生、1,248 场会话，覆盖完整学期。在公开评测协议下，其基础质量达标，工作同盟指标超过所有单会话语料库；在 CPCD 上微调的模型比无事件依赖训练的模型更常将每周事件与先前事件关联。
正文 · 原文
Abstract:Psychological counseling unfolds over many sessions, and what a client brings to each session depends on what has happened in their life since the last one. Existing synthetic counseling corpora are mostly single-session, and multi-session ones advance along a therapy plan without modeling the client's life between sessions. We present Psy-Chronicle, an event-driven framework that grounds multi-session counseling synthesis in a student's semester timeline: each simulated student receives a profile and a semester-long temporal stress event graph, and counseling sessions are generated along this timeline with memory carried across them. Applied to campus counseling, it yields CPCD, an open Chinese dataset of 100 students and 1{,}248 sessions spanning a full semester. The dialogues follow their timelines: dependencies between events carry across sessions, and references to earlier sessions rarely introduce content absent from the trajectory. Under a published evaluation protocol, in basic quality and exceeds all single-session corpora in working alliance. A model fine-tuned on CPCD connects each week's events to earlier ones more often than a model trained on the same data without the dependencies between events, while matching it when the client's situation does not change.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2605.22140 [cs.CL] |
| (or arXiv:2605.22140v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.22140 arXiv-issued DOI via DataCite |
Submission history
From: Chaogui Gou [view email]
[v1]
Thu, 21 May 2026 08:12:53 UTC (3,755 KB)
[v2]
Wed, 8 Jul 2026 07:04:53 UTC (1,363 KB)
[v3]
Tue, 20 Oct 2026 03:27:21 UTC (154 KB)
来源：arXiv cs.CL · arxiv.org