大型语言模型在多大程度上捕捉人类个性？
How Well Do Large Language Models Capture Human Personality?
AI总结：
研究通过形式化假设并系统评估，发现增加角色描述复杂性会导致表征和行为多样性收缩（角色流形坍缩），简单年龄-性别角色比丰富描述更准确。
摘要：
大型语言模型（LLMs）越来越多地通过角色提示用于模拟人类群体，通常基于以下假设：更丰富的角色描述能提高行为保真度、相同大小的属性组合可同等模拟、角色定义可跨任务泛化。在这项工作中，我们形式化了这些假设，并在多种架构、规模和模拟设置下系统评估它们。我们识别出一个基本限制，称为角色流形坍缩，即越来越具表现力的角色规范导致表征和行为多样性的系统性收缩。跨模型而言，增加角色复杂性持续降低潜在空间中角色间的分离度，并削弱下游模拟任务中的行为分化。这些效应在多项分析中持续存在：更丰富的角色未能保留人类子群体分歧，相同大小的属性组合性能各异，添加描述细节往往降低而非提高模拟保真度。令人惊讶的是，简单的年龄-性别角色在多个行业中持续优于详细指定的理想客户画像（ICPs），实现了显著更高的下游预测准确性。我们发现坍缩并非在所有属性上均匀发生。某些组合在行为上保持稳定，并与人类响应保持更强的一致性，形成我们称为对齐桥的局部区域。总之，我们的结果为理解角色条件模拟的局限性提供了经验和概念基础，强调了需要构建表征感知的角色，而非仅仅增加角色表现力。
英文摘要：
Large language models (LLMs) are increasingly used to simulate human populations via persona prompting, often under the assumptions that richer persona descriptions improve behavioral fidelity, similarly sized attribute combinations are equally simulatable, and persona definitions generalize across tasks. In this work, we formalize these assumptions and systematically evaluate them across multiple architectures, scales, and simulation settings. We identify a fundamental limitation we term persona manifold collapse, where increasingly expressive persona specifications lead to systematic contraction of representational and behavioral diversity. Across models, increasing persona complexity consistently reduces inter-persona separation in latent space and weakens behavioral differentiation in downstream simulation tasks. These effects persist across multiple analyses as richer personas fail to preserve human subgroup disagreement, performance varies across attribute combinations of similar size, and adding descriptive detail often degrades rather than improves simulation fidelity. Surprisingly, simple Age-Gender personas consistently outperform richly specified Ideal Customer Profiles (ICPs) across industries, achieving substantially higher downstream prediction accuracy. We find that collapse is not uniform across attributes. Certain combinations remain behaviorally stable and preserve stronger alignment with human responses, forming localized regions we term alignment bridges. Together, our results provide empirical and conceptual foundations for understanding the limits of persona-conditioned simulation, highlighting the need for representation-aware persona construction rather than increasing persona expressivity alone.
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。
