通过纵向生活轨迹缓解大语言模型智能体中的本质主义身份偏差
Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories
浏览论文内容
中文总结 AI 辅助
针对现有LLM智能体存在的身份本质主义偏差导致组内反应同质化的问题，提出LifeMem纵向记忆框架，在Add Health等数据集上验证其可提升与人类数据的一致性。
中文摘要 AI 辅助
大语言模型（LLMs）为社会模拟提供了一种可扩展的方法，但其可信度取决于智能体的构建方式。现有方法能够部分复现群体层面的模式，但往往无法捕捉类人的多样性。我们的分析表明，静态 profile 智能体表现出比人类更强的人口统计学分离度和组内压缩，这种模式与身份本质主义一致：人口统计学标签可能会鼓励模型将群体平均倾向视为个体特质，从而使组内反应同质化。我们认为，这一局限性源于两个相关因素：稀疏的静态智能体表示，以及仅基于提示的记忆无法持续整合经验的能力。受互补记忆系统的启发，我们提出 LifeMem，这是一种纵向记忆框架，将结构化生活事件检索与特定智能体的参数化记忆相结合，用于经验整合。在 Add Health 和 Understanding Society 数据集上使用三种 LLM 进行的实验表明，LifeMem 在反应分布、整体及组内多样性、以及跨人生阶段的个人内反应变化模式方面，提高了与人类数据的一致性。这些发现凸显了纵向生活事件记忆对于构建更忠实、动态演化的社会智能体的价值。
英文摘要
Large language models (LLMs) offer a scalable approach to social simulation, but their credibility depends on how agents are constructed. Existing methods can partially reproduce population-level patterns, yet often fail to capture human-like diversity. Our analysis shows that static-profile agents exhibit stronger demographic separation and within-group compression than humans, a pattern consistent with identity essentialism: demographic labels can encourage models to treat group-average tendencies as individual traits, homogenizing responses within groups. We argue that this limitation arises from two related factors: sparse, static agent representations and the limited ability of prompt-only memory to persistently integrate experience. Inspired by complementary memory systems, we propose LifeMem, a longitudinal memory framework that combines structured life-event retrieval with agent-specific parametric memory for experience integration. Experiments on Understanding Society with three LLMs show that LifeMem improves alignment with human data in terms of response distributions, overall and within-group diversity, and patterns of within-person response change across life stages. These findings highlight the value of longitudinal life-event memory for constructing more faithful and dynamically evolving social agents.
