Live intelligence

Latest AI updates

2 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
Research Editor selected

Therapy-FIS: First Public Dataset for Automated Assessment of Therapist Interpersonal Skills

Therapy-FIS is a new dataset for automated assessment of Facilitative Interpersonal Skills (FIS) in psychotherapy, containing facial, acoustic, and textual signals from 890 therapist recordings and 8 patient videos. It includes eight FIS subscale ratings and an overall score, and supports two benchmark tasks: Therapist Performance Rating and Joint Therapist–mock-Patient Performance Rating. The authors also introduce a baseline model, DyadicFIS, which achieves best macro CCC scores of 0.2807 and 0.3299 on the two tasks.

Why it matters: This is the first publicly available dataset for automated FIS assessment, addressing a critical data scarcity and enabling reproducible research in mental health AI.

Facilitative Interpersonal SkillsAutomated assessmentMental health AI