Live intelligence

Latest AI updates

1 updates
Research

CounselTraj: Dialogue-Act Trajectory Planning for Session-Level Synthetic Counseling Dialogues

CounselTraj is a dialogue-act trajectory planning framework that expands brief synthetic counseling dialogues into process-aware, session-level conversations. It learns dialogue-act patterns from role-play counseling dialogues produced by human counselors, then plans coordinated client and counselor trajectories to guide long-form generation. Experiments on three Chinese synthetic counseling datasets show more complete and coherent sessions with higher-quality counselor interventions than direct expansion or randomly sampled trajectories. The authors release CounselTrajD, a dataset of over 10K process-guided Chinese counseling dialogues, and train CounselTrajLM, which outperforms publicly available Chinese counseling models on response quality, therapeutic understanding and intervention, and process coherence.

LLM dialogue generationmental health AIsynthetic data