心智競技場：自我對弈訓練語言模型以診斷和治療心理健康疾病。

MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders

October 9, 2024

作者: Cheng Li, May Fung, Qingyun Wang, Chi Han, Manling Li, Jindong Wang, Heng Ji

cs.AI

摘要

心理健康疾病是世界上最嚴重的疾病之一。大多數患有此類疾病的人缺乏適當的護理，這凸顯了為心理健康疾病的診斷和治療訓練模型的重要性。然而，在心理健康領域，隱私問題限制了個性化治療數據的可訪問性，這使得建立強大模型具有挑戰性。在本文中，我們介紹了MentalArena，這是一個自我對弈框架，通過生成特定領域的個性化數據來訓練語言模型，在這裡我們獲得了一個更好的模型，能夠進行個性化診斷和治療（作為治療師）並提供信息（作為患者）。為了準確建模類似人類的心理健康患者，我們設計了症狀編碼器，它從認知和行為兩個角度模擬了一個真實的患者。為了應對患者-治療師互動中的意圖偏見，我們提出了症狀解碼器，以比較診斷症狀與編碼症狀，並根據識別的偏差動態管理患者和治療師之間的對話。我們對MentalArena進行了評估，包括生物醫學問答和心理健康任務，與6個先進模型進行了比較。我們的模型在GPT-3.5和Llama-3-8b上進行了微調，明顯優於其對應的模型，包括GPT-4o。我們希望我們的工作能激發未來個性化護理研究。代碼可在https://github.com/Scarelette/MentalArena/tree/main找到。

English

Mental health disorders are one of the most serious diseases in the world. Most people with such a disease lack access to adequate care, which highlights the importance of training models for the diagnosis and treatment of mental health disorders. However, in the mental health domain, privacy concerns limit the accessibility of personalized treatment data, making it challenging to build powerful models. In this paper, we introduce MentalArena, a self-play framework to train language models by generating domain-specific personalized data, where we obtain a better model capable of making a personalized diagnosis and treatment (as a therapist) and providing information (as a patient). To accurately model human-like mental health patients, we devise Symptom Encoder, which simulates a real patient from both cognition and behavior perspectives. To address intent bias during patient-therapist interactions, we propose Symptom Decoder to compare diagnosed symptoms with encoded symptoms, and dynamically manage the dialogue between patient and therapist according to the identified deviations. We evaluated MentalArena against 6 benchmarks, including biomedicalQA and mental health tasks, compared to 6 advanced models. Our models, fine-tuned on both GPT-3.5 and Llama-3-8b, significantly outperform their counterparts, including GPT-4o. We hope that our work can inspire future research on personalized care. Code is available in https://github.com/Scarelette/MentalArena/tree/main