发表机构
University of Southern California; Center for Democracy and Technology（南加州大学; 民主与技术中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究发现LLM的文化表征在空间上接近当前实际情况，但时间上滞后数年，仅能捕捉部分文化变迁，存在时间扁平化问题，揭示了快照式评估的局限性。
AI 中文摘要
文化对齐评估已成为大型语言模型（LLM）开发与改进的重要组成部分。然而，大多数评估将文化视为单一快照，仅研究模型是否能准确表征当前某一社会的文化。文化心理学研究表明，文化价值观会随时间以不同的速率和方向发生变化。因此，“具有文化意识”的模型不仅应捕捉文化当下的状态，还应捕捉其随时间的变化。我们利用二十多年的世界价值观调查（World Values Survey）数据，考察文化意识的这一缺失维度。我们在英格尔哈特-韦尔策尔（Inglehart-Welzel）文化地图上，将40个国家的文化轨迹与四个最先进（SOTA）LLM生成的轨迹进行比较。我们的研究结果显示，虽然这些模型通常将国家置于其最新调查位置附近，但这些表征往往滞后于该位置数年；它们仅能捕捉到观测到的部分变化幅度，在几乎没有变化的地方引入了变动，且很少能再现国家轨迹的逆转。这些发现指出了时间扁平化问题，表明快照式的准确性可能无法全面反映LLM的文化意识，对模型评估、表征性伤害以及具有文化意识的AI系统的治理具有启示意义。
英文摘要
Assessments of cultural alignment have become an important part of the development and improvement of large language models (LLMs). However, the majority of the evaluations treat culture as a single snapshot, investigating only whether a model represents a society accurately at the current time. Research in cultural psychology shows that cultural values change at different rates and directions over time. Therefore, a "culturally aware" model should capture not only where a culture is today but also how it has changed over time. We examine this missing dimension of cultural awareness using more than two decades of the World Values Survey data. We compare the cultural trajectories of 40 countries with the trajectories produced by four state-of-the-art (SOTA) LLMs on the Inglehart-Welzel cultural map. Our findings show that while models generally place countries close to their most recent surveyed positions, these representations tend to lag several years behind that position. They also capture only part of the magnitude of the observed change, introduce movement where little occurred, and rarely reproduce reversals in countries' trajectories. These findings point to temporal flattening and suggest that snapshot accuracy can give an incomplete picture of cultural awareness in LLMs and have implications for model evaluation, representational harms, and the governance of culturally aware AI systems.
Comments38 pages, 12 figures, 36 tables; includes Supplementary Materials
