Researchers have developed CounselTraj, a framework designed to generate longer, process-aware psychological counseling dialogues from shorter synthetic exchanges. This method learns dialogue-act patterns from human-led role-play sessions to plan coordinated trajectories for both clients and counselors, guiding the creation of more coherent and complete dialogues. The framework has been used to construct a dataset of over 10,000 Chinese counseling dialogues, which then trained a model, CounselTrajLM, outperforming existing Chinese counseling models in response quality and therapeutic coherence. AI
IMPACT This research could lead to more sophisticated AI tools for mental health support by improving the quality and coherence of synthetic counseling dialogues.
RANK_REASON This is a research paper detailing a new framework and dataset for dialogue generation. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →