[论文解读] Towards a Psychological Generalist AI: A Survey of Current Applications of Large Language Models and Future Prospects

Tianyu He, Guanghui Fu+9 more|arXiv (Cornell University)|Dec 1, 2023

Digital Mental Health Interventions被引用 9

一句话总结

本文综述了大型语言模型在心理学中的应用，讨论了模型验证，并概述了精神健康领域通用人工智能的未来前景与挑战。

ABSTRACT

The complexity of psychological principles underscore a significant societal challenge, given the vast social implications of psychological problems. Bridging the gap between understanding these principles and their actual clinical and real-world applications demands rigorous exploration and adept implementation. In recent times, the swift advancement of highly adaptive and reusable artificial intelligence (AI) models has emerged as a promising way to unlock unprecedented capabilities in the realm of psychology. This paper emphasizes the importance of performance validation for these large-scale AI models, emphasizing the need to offer a comprehensive assessment of their verification from diverse perspectives. Moreover, we review the cutting-edge advancements and practical implementations of these expansive models in psychology, highlighting pivotal work spanning areas such as social media analytics, clinical nursing insights, vigilant community monitoring, and the nuanced exploration of psychological theories. Based on our review, we project an acceleration in the progress of psychological fields, driven by these large-scale AI models. These future generalist AI models harbor the potential to substantially curtail labor costs and alleviate social stress. However, this forward momentum will not be without its set of challenges, especially when considering the paradigm changes and upgrades required for medical instrumentation and related applications.

研究动机与目标

• 评估在数字媒体、临床护理和社区环境中，LLM在心理学中的当前使用情况。
• 突出在心理学情境中对LLM的验证框架与评估任务。
• 讨论多模态通用型AI、伦理监控，以及心理学领域的现实世界部署挑战。
• 概述对心理治疗、诊断和心理健康支持的潜在应用与意义。

提出的方法

• 评审跨越社交媒体分析、临床护理与社区监测等领域的现有文献。
• 概括心理学中的任务特定评估方法（如情感识别、抑郁与自杀风险检测）。
• 讨论用于评估心理学中LLM能力的评估平台和数据集（如CLEVA、CHBias）。
• 综合LLM（GPT系列）在数字平台、临床环境与理论发展方面的进展。

Figure 1: Future applications of GPAI. (a) GPAI monitors patient health in the ward (b) GPAI assists doctors in psychological consultation (c) GPAI assists doctors in analyzing and diagnosing psychological data (d) GPAI supports people with negative emotions in social media.

实验结果

研究问题

• RQ1 大型语言模型在心理学中在不同场景下的当前应用有哪些？
• RQ2 LLM在心理学任务与特征方面如何进行验证与评估？
• RQ3 通用型AI在心理治疗、心理健康监测和研究中未来可能扮演哪些角色？
• RQ4 在心理学语境中部署LLM时伴随的伦理、技术与实际挑战有哪些？

主要发现

• LLMs被应用于社交媒体与临床数据中的情感分析、自杀风险检测、认知扭曲和情绪识别。
• 任务表现随数据集和任务复杂性而异，微调在某些结果上有提升，但并非所有认知扭曲任务都有效。
• 评估框架（如CLEVA、CHBias）和特定任务指标对于理解LLM在心理学中的能力至关重要。
• 多模态与交互能力使GPAI能够监测、协助临床医生，并支持有负面情绪的个体。
• 在精神健康环境中部署LLM存在显著的伦理、偏见与治理方面的考量。

Figure 2: Applications of GPAI in various aspects of psychology.