跳到正文
arXiv cs.AI· Zhiyang Qi, Michimasa Inaba·· 10 小时前AI 评分31

CounselTraj:通过对话行为轨迹规划合成过程感知的心理咨询对话

CounselTraj: Synthesizing Process-Aware Psychological Counseling Dialogues via Dialogue-Act Trajectory Planning

AI 导读

CounselTraj 是一个对话行为轨迹规划框架,可将简短合成对话扩展为过程感知的会话级心理咨询对话,在三个中文合成咨询数据集上生成的会话更完整连贯、咨询师干预质量更高。

正文 · 原文

View PDF HTML (experimental)

Abstract:The growing demand for psychological counseling has motivated the development of LLM-based systems that support human counselors, but training such systems requires large-scale, high-quality dialogue data. Authentic counseling transcripts are difficult to collect and share because of privacy concerns, making synthetic dialogues an important alternative. However, existing synthetic datasets, despite covering diverse scenarios and client profiles, often consist of brief exchanges and fail to capture session-level counseling processes. We propose CounselTraj, a dialogue-act trajectory planning framework for expanding brief synthetic dialogues into process-aware, session-level psychological counseling dialogues. CounselTraj learns dialogue-act patterns from role-play counseling dialogues produced by human counselors, plans coordinated trajectories for clients and counselors, and uses them as flexible guidance for long-form dialogue generation. Experiments across three Chinese synthetic counseling datasets show that CounselTraj produces more complete and coherent sessions with higher-quality counselor interventions than both direct expansion and expansion with randomly sampled trajectories. Based on CounselTraj, we construct CounselTrajD, a dataset containing over 10K process-guided Chinese psychological counseling dialogues, and use it to train CounselTrajLM for counseling response generation. Evaluations at both the response and session levels show that CounselTrajLM outperforms publicly available Chinese counseling models in response quality, therapeutic understanding and intervention, and counseling-process coherence and progress. Our code and model are publicly available at this https URL.
Comments: Accepted to EACL 2027 Main Conference
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.24168 [cs.CL]
  (or arXiv:2611.24168v1 [cs.CL] for this version)
  https://doi.org/10.48550/arXiv.2611.24168

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Zhiyang Qi [view email]
[v1] Wed, 18 Nov 2026 10:10:54 UTC (448 KB)

来源:arXiv cs.AI · arxiv.org