Psy-Chronicle:A Structured Pipeline for Synthesizing Long-Horizon Campus Psychological Counseling Dialogues
arXiv:2605.22140v1 Announce Type: new Abstract: In recent years, large language models have shown substantial potential in psychological support tasks. However, existing psychological counseling data mostly rely on single-turn question answering or short multi-turn dialogues, making it difficult to characterize how college students' psychological distress accumulates, interacts, and gradually evolves over long periods within campus life events. To address this issue, this paper proposes Psy-Chronicle, a structured data-generation framework for synthesizing long-horizon campus psychological cou
The proliferation of advanced large language models enables more sophisticated approaches to synthesizing complex, long-horizon data for specialized applications like psychological counseling.
This development indicates a significant advancement in AI's capacity to handle nuanced, multi-turn interactions, extending beyond simple Q&A to address complex personal issues over time.
AI systems can now be trained on synthetically generated, long-form conversational data specifically designed to simulate and address evolving psychological distress, improving the fidelity and utility of AI in mental health support.
- · AI developers
- · Mental health support platforms
- · Educational institutions
- · Students experiencing distress
- · Traditional short-form counseling data providers
- · AI models lacking long-context understanding
AI-powered psychological support tools will become more effective and personalized for long-term user engagement.
The improved efficacy of AI in mental health may lead to its broader adoption in educational and corporate wellbeing programs.
This could potentially democratize access to scalable, consistent psychological support, impacting global mental health outcomes and reducing the burden on human counselors for routine cases.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL