arXiv 2412.168822025-01-01cs.AIcs.CL

PsychAdapter：适配LLM Transformer以反映特质、人格与心理健康

PsychAdapter: Adapting LLM Transformers to Reflect Traits, Personality and Mental Health

Stony Brook University（石溪大学）；New York University（纽约大学）；University of Melbourne（墨尔本大学）；University of Texas at Dallas（德克萨斯大学达拉斯分校）；University of Pennsylvania（宾夕法尼亚大学）；Stanford University（斯坦福大学）

Huy Vu, Huy Anh Nguyen, Adithya V Ganesan, Swanie Juhng, Oscar N. E. Kjell, Joao Sedoc, Margaret L. Kern, Ryan L. Boyd, Lyle Ungar, H. Andrew Schwartz, Johannes C. Eichstaedt

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

PsychAdapter通过对Transformer各层进行轻量级适配，将经验性特质—语言模式注入GPT-2、Gemma和Llama 3，使其无需提示即可生成符合指定人格、人口学及心理健康特征的自然语言，并实现高准确率匹配。

摘要：

基于人工智能的语言生成器如今已成为大多数人生活的一部分。然而，默认情况下，它们倾向于生成“平均化”的语言，而无法反映人与人之间的差异。在此，我们提出对标准语言模型Transformer架构的一种轻量级修改——“PsychAdapter”，它利用经验推导的特质—语言模式，为指定的人格、人口统计学和心理健康特征生成自然语言（无论是否使用提示）。我们将PsychAdapter应用于修改OpenAI的GPT-2、Google的Gemma和Meta的Llama 3，并发现生成的文本能够反映所期望的特质。例如，专家评分者评估了PsychAdapter生成的文本输出，发现其匹配预期特质水平的平均准确率在大五人格上为87.3%，在抑郁和生活满意度上为96.7%。PsychAdapter是一种新颖的方法，通过在基础层面影响每一个Transformer层，将心理行为模式引入语言模型，且独立于提示。该方法可以创建具有特定人格画像的聊天机器人、反映与心理状况相关语言的临床训练工具，以及匹配作者阅读或教育水平的机器翻译，而无需占用LLM的上下文窗口。PsychAdapter还允许通过自然语言表达来探索心理学构念，从而扩展自然语言处理工具箱以研究人类心理学。

英文摘要：

Artificial intelligence-based language generators are now a part of most people's lives. However, by default, they tend to generate "average" language without reflecting the ways in which people differ. Here, we propose a lightweight modification to the standard language model transformer architecture - "PsychAdapter" - that uses empirically derived trait-language patterns to generate natural language for specified personality, demographic, and mental health characteristics (with or without prompting). We applied PsychAdapters to modify OpenAI's GPT-2, Google's Gemma, and Meta's Llama 3 and found generated text to reflect the desired traits. For example, expert raters evaluated PsychAdapter's generated text output and found it matched intended trait levels with 87.3% average accuracy for Big Five personalities, and 96.7% for depression and life satisfaction. PsychAdapter is a novel method to introduce psychological behavior patterns into language models at the foundation level, independent of prompting, by influencing every transformer layer. This approach can create chatbots with specific personality profiles, clinical training tools that mirror language associated with psychological conditionals, and machine translations that match an authors reading or education level without taking up LLM context windows. PsychAdapter also allows for the exploration psychological constructs through natural language expression, extending the natural language processing toolkit to study human psychology.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。