paper-with-me

홈 › Papers

Multi-Objective Alignment of Language Models for Personalized Psychotherapy

2026-02-17 · Mehrab Beikzadeh, Yasaman Asadollah Salmanpour, Ashima Suvarna, Sriram Sankararaman, Matteo Malgaroli, Majid Sarrafzadeh, Saadia Gabriel arxiv

Mental health disorders affect over 1 billion people worldwide, yet access to care remains limited by workforce shortages and cost constraints. While AI systems show therapeutic promise, current alignment approaches optimize objectives independently, failing to balance patient preferences with clinical safety. We survey 335 individuals with lived mental health experience to collect preference rankings across therapeutic dimensions, then develop a multi-objective alignment framework using direct preference optimization. We train reward models for six criteria -- empathy, safety, active listening, self-motivated change, trust/rapport, and patient autonomy -- and systematically compare multi-objective approaches against single-objective optimization, supervised fine-tuning, and parameter merging. Multi-objective DPO (MODPO) achieves superior balance (77.6% empathy, 62.6% safety) compared to single-objective optimization (93.6% empathy, 47.8% safety), and therapeutic criteria outperform general communication principles by 17.2%. Blinded clinician evaluation confirms MODPO is consistently preferred, with LLM-evaluator agreement comparable to inter-clinician reliability.

📄 PDF Abstract BibTeX arXiv:2602.16053

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directions

2025-02-16 · Hongbin Na, Yining Hua, Zimu Wang, Tao Shen 외

Mental health remains a critical global challenge, with increasing demand for accessible, effective interventions. Large language models (LLMs) offer promising solutions in psychotherapy by enhancing the assessment, diag…

Survey

Psychotherapy AI Companion with Reinforcement Learning Recommendations and Interpretable Policy Dynamics

2023-03-16 · Baihan Lin, Guillermo Cecchi, Djallel Bouneffouf

We introduce a Reinforcement Learning Psychotherapy AI Companion that generates topic recommendations for therapists based on patient responses. The system uses Deep Reinforcement Learning (DRL) to generate multi-objecti…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Advancing Conversational Psychotherapy: Integrating Privacy, Dual-Memory, and Domain Expertise with Large Language Models

2024-12-04 · XiuYu Zhang, Zening Luo

Mental health has increasingly become a global issue that reveals the limitations of traditional conversational psychotherapy, constrained by location, time, expense, and privacy concerns. In response to these challenges…

ChatbotLarge Language ModelRAGRetrieval-augmented Generation

Rethinking the Alignment of Psychotherapy Dialogue Generation with Motivational Interviewing Strategies

2024-08-12 · Xin Sun, Xiao Tang, Abdallah El Ali, Zhuying Li 외

Recent advancements in large language models (LLMs) have shown promise in generating psychotherapeutic dialogues, particularly in the context of motivational interviewing (MI). However, the inherent lack of transparency …

Dialogue Generation

MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models

2026-05-25 · Linhao Luo, Thuy-Trang Vu, Van-Anh Nguyen, Junae Kim 외 arxiv

Aligning large language models (LLMs) with diverse and multifaceted user preferences is a fundamental challenge in personalized AI systems. Existing multi-objective alignment methods either rely on costly training or req…