大型语言模型的情感智能
Emotional Intelligence of Large Language Models
AI总结：
本文通过开发针对情感理解的心理测量评估方法，系统测试了大型语言模型的情感智能，发现GPT-4等模型EQ超越多数人类，但其内在表征机制与人类存在显著差异。
摘要：
大型语言模型（LLMs）在众多学科中展现出了卓越的能力，这主要通过语言生成、知识利用和复杂推理等任务来评估。然而，它们与人类情感和价值观的契合度对于现实世界应用至关重要，却尚未得到系统性评估。在此，我们评估了LLMs的情感智能（EI），包括情感识别、解释和理解，这对于有效沟通和社交互动是必不可少的。具体而言，我们首先开发了一种新颖的心理测量评估方法，专注于EI的核心组成部分——情感理解（EU），该方法适用于人类和LLMs。该测试要求在现实场景中评估复杂情感（例如，尽管感觉表现不佳，John却出人意料地获得了最高分，涉及惊讶、喜悦、困惑、自豪等情感）。基于由超过500名成年人构建的参考框架，我们测试了多种主流LLMs。大多数模型取得了高于平均水平的EQ分数，其中GPT-4的EQ达到117，超越了89%的人类参与者。有趣的是，多元模式分析显示，一些LLMs显然并未依赖类人机制来实现人类水平的性能，因为它们的表征模式与人类在性质上存在显著差异。此外，我们还讨论了模型规模、训练方法和架构等因素对LLMs的EQ的影响。综上所述，我们的研究是对LLMs类人特征的首批心理测量评估之一，这可能为未来旨在实现高智力与高情感智能的LLMs开发提供启示。项目网站：https://emotional-intelligence.github.io/
英文摘要：
Large Language Models (LLMs) have demonstrated remarkable abilities across numerous disciplines, primarily assessed through tasks in language generation, knowledge utilization, and complex reasoning. However, their alignment with human emotions and values, which is critical for real-world applications, has not been systematically evaluated. Here, we assessed LLMs' Emotional Intelligence (EI), encompassing emotion recognition, interpretation, and understanding, which is necessary for effective communication and social interactions. Specifically, we first developed a novel psychometric assessment focusing on Emotion Understanding (EU), a core component of EI, suitable for both humans and LLMs. This test requires evaluating complex emotions (e.g., surprised, joyful, puzzled, proud) in realistic scenarios (e.g., despite feeling underperformed, John surprisingly achieved a top score). With a reference frame constructed from over 500 adults, we tested a variety of mainstream LLMs. Most achieved above-average EQ scores, with GPT-4 exceeding 89% of human participants with an EQ of 117. Interestingly, a multivariate pattern analysis revealed that some LLMs apparently did not reply on the human-like mechanism to achieve human-level performance, as their representational patterns were qualitatively distinct from humans. In addition, we discussed the impact of factors such as model size, training method, and architecture on LLMs' EQ. In summary, our study presents one of the first psychometric evaluations of the human-like characteristics of LLMs, which may shed light on the future development of LLMs aiming for both high intellectual and emotional intelligence. Project website: https://emotional-intelligence.github.io/
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。
