coTherapist: A Behavior-Aligned Small Language Model to Support Mental Healthcare Experts

TL;DR

coTherapist is a small language model designed to support mental health professionals by providing relevant, empathetic, and safe responses, demonstrating that small models can emulate expert therapeutic behaviors effectively.

Contribution

This work introduces coTherapist, a novel small language model framework that incorporates domain-specific fine-tuning, retrieval, and reasoning to support mental healthcare, validated by clinical expert evaluations.

Findings

Outperforms baseline models in clinical relevance

Exhibits high empathy and therapist-like traits

Delivers accurate, trustworthy, and safe responses

Abstract

Access to mental healthcare is increasingly strained by workforce shortages and rising demand, motivating the development of intelligent systems that can support mental healthcare experts. We introduce coTherapist, a unified framework utilizing a small language model to emulate core therapeutic competencies through domain-specific fine-tuning, retrieval augmentation, and agentic reasoning. Evaluation on clinical queries demonstrates that coTherapist generates more relevant and clinically grounded responses than contemporary baselines. Using our novel T-BARS rubric and psychometric profiling, we confirm coTherapist exhibits high empathy and therapist-consistent personality traits. Furthermore, human evaluation by domain experts validates that coTherapist delivers accurate, trustworthy, and safe responses. coTherapist was deployed and tested by clinical experts. Collectively, these findings demonstrate that small models can be engineered to exhibit expert-like behavior, offering a scalable pathway for digital mental health tools.