# Preference Learning Unlocks LLMs' Psycho-Counseling Skills

arXiv: https://arxiv.org/abs/2502.19731 · HTML: https://mlsanity.com/paper/2502.19731/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Medical LLM alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 29 of its 45 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Medical LLM alignment](https://mlsanity.com/alignment/medical-llm-alignment/)

## Builds on (most cited first, 29 of 29)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies](https://mlsanity.com/paper/2404.06395/) (2024)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs](https://mlsanity.com/paper/2410.18451/) (2024)
- [OLMoE: Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2409.02060/) (2024)
- [Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study](https://mlsanity.com/paper/2404.10719/) (2024)
- [Iterative Reasoning Preference Optimization](https://mlsanity.com/paper/2404.19733/) (2024)
- [Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms](https://mlsanity.com/paper/2406.02900/) (2024)
- [HelpSteer2-Preference: Complementing Ratings with Preferences](https://mlsanity.com/paper/2410.01257/) (2024)
- [Understanding the performance gap between online and offline alignment algorithms](https://mlsanity.com/paper/2405.08448/) (2024)
- [Facilitating Self-Guided Mental Health Interventions Through Human-Language Model Interaction: A Case Study of Cognitive Restructuring](https://mlsanity.com/paper/2310.15461/) (2023)
- [ChatCounselor: A Large Language Models for Mental Health Support](https://mlsanity.com/paper/2309.15461/) (2023)
- [LLM-empowered Chatbots for Psychiatrist and Patient Simulation: Application and Evaluation](https://mlsanity.com/paper/2305.13614/) (2023)
- [Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts](https://mlsanity.com/paper/2307.02768/) (2023)
- [Empowering Psychotherapy with Large Language Models: Cognitive Distortion Detection through Diagnosis of Thought Prompting](https://mlsanity.com/paper/2310.07146/) (2023)
- [Challenges of Large Language Models for Mental Health Counseling](https://mlsanity.com/paper/2311.13857/) (2023)
- [CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy](https://mlsanity.com/paper/2410.13218/) (2024)
- [A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directions](https://mlsanity.com/paper/2502.11095/) (2025)
- [MentalAgora: A Gateway to Advanced Personalized Care in Mental Health through Multi-Agent Debating and Attribute Control](https://mlsanity.com/paper/2407.02736/) (2024)
- [Orion-14B: Open-source Multilingual Large Language Models](https://mlsanity.com/paper/2401.12246/) (2024)

## Built on by (most cited first, 10 of 10)

- [SoSBench: Benchmarking Safety Alignment on Six Scientific Domains](https://mlsanity.com/paper/2505.21605/) (2025)
- [TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling](https://mlsanity.com/paper/2510.25758/) (2025)
- [Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors](https://mlsanity.com/paper/2504.20106/) (2025)
- [PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions](https://mlsanity.com/paper/2509.07370/) (2025)
- [Do No Harm: Exposing Hidden Vulnerabilities of LLMs via Persona-based Client Simulation Attack in Psychological Counseling](https://mlsanity.com/paper/2604.04842/) (2026)
- [PSI-Bench: Interpretable and Clinically Meaningful Evaluation of Depression Patient Simulators](https://mlsanity.com/paper/2604.25840/) (2026)
- [TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots](https://mlsanity.com/paper/2603.18008/) (2026)
- [Discourse Diversity in Multi-Turn Empathic Dialogue](https://mlsanity.com/paper/2604.11742/) (2026)
- [From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health](https://mlsanity.com/paper/2609.25186/) (2026)
- [PsyEvo: A Personalized Counseling Agent That Self-Evolves at Test Time](https://mlsanity.com/paper/2610.02885/) (2026)

## Abstract (arXiv)

Applying large language models (LLMs) to assist in psycho-counseling is an emerging and meaningful approach, driven by the significant gap between patient needs and the availability of mental health support. However, current LLMs struggle to consistently provide effective responses to client speeches, largely due to the lack of supervision from high-quality real psycho-counseling data, whose content is typically inaccessible due to client privacy concerns. Furthermore, the quality of therapists' responses in available sessions can vary significantly based on their professional training and experience. Assessing the quality of therapists' responses remains an open challenge. In this work, we address these challenges by first proposing a set of professional and comprehensive principles to evaluate therapists' responses to client speeches. Using these principles, we create a preference dataset, PsychoCounsel-Preference, which contains 36k high-quality preference comparison pairs. This dataset aligns with the preferences of professional psychotherapists, providing a robust foundation for evaluating and improving LLMs in psycho-counseling. Experiments on reward modeling and preference learning demonstrate that PsychoCounsel-Preference is an excellent resource for LLMs to acquire essential skills for responding to clients in a counseling session. Our best-aligned model, PsychoCounsel-Llama3-8B, achieves an impressive win rate of 87% against GPT-4o. We release PsychoCounsel-Preference, PsychoCounsel-Llama3-8B and the reward model PsychoCounsel Llama3-8B-Reward to facilitate the research of psycho-counseling with LLMs at: https://hf.co/Psychotherapy-LLM.