mlsanityData to 13 Oct 2026

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

arXiv 2601.10246 ↗First posted 15 Jan 2026cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 24 of its 71 references that are in the map. First posted on arXiv 15 Jan 2026.

Builds on

24 of 71 references.

References · 24

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,231
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,492
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,480
  4. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,388
  5. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,556
  6. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,200
  7. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,120
  8. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 557
  9. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 195
  10. 2023Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Datacited by 66
  11. 2023Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMscited by 62
  12. 2024A Computational Framework for Behavioral Assessment of LLM Therapistscited by 62
12 more
  1. 2023Facilitating Self-Guided Mental Health Interventions Through Human-Language Model Interaction: A Case Study of Cognitive Restructuringcited by 53
  2. 2024BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Datacited by 49
  3. 2021InfoLM: A New Metric to Evaluate Summarization & Data2Text Generationcited by 33
  4. 2024Guiding Clinical Reasoning with Large Language Models via Knowledge Seedscited by 19
  5. 2025Exploring the Impact of Personality Traits on LLM Bias and Toxicitycited by 14
  6. 2024Exploring the Efficacy of Large Language Models in Summarizing Mental Health Counseling Sessions: A Benchmark Studycited by 13
  7. 2023Response-act Guided Reinforced Dialogue Generation for Mental Health Counselingcited by 9
  8. 2024TutoAI: A Cross-domain Framework for AI-assisted Mixed-media Tutorial Creation on Physical Taskscited by 6
  9. 2025From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilerscited by 5
  10. 2025Large Language Models for Scientific Idea Generation: A Creativity-Centered Surveycited by 5
  11. 2025A Comprehensive Review of Datasets for Clinical Mental Health AI Systemscited by 3
  12. 2025AI-Augmented LLMs Achieve Therapist-Level Responses in Motivational Interviewingcited by 1

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QAcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MindEval: Benchmarking Language Models on Multi-turn Mental Health Support
  2. 2026Mind Companion: An Embodied Conversational Agent for Process-Based Psychotherapy
  3. 2026CPEMH: An Agentic Framework for Prompt-Driven Behavior Evaluation and Assurance in Foundation-Model Systems for Mental Health Screening
  4. 2026Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teaming
  5. 2026TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots
  6. 2026PAIR-SAFE: A Paired-Agent Approach for Runtime Auditing and Refining AI-Mediated Mental Health Support
  7. 2025WiseMind: a knowledge-guided multi-agent framework for accurate and empathetic psychiatric diagnosis
  8. 2026Reasoning Over Recall: Evaluating the Efficacy of Generalist Architectures vs. Specialized Fine-Tunes in RAG-Based Mental Health Dialogue Systems