LLM人格的双重性质：聚合倾向与框架依赖的几何结构
Cultural Bias Without a Cultural Self:A Disassociation Study of LLM's Persona and Bias
浏览论文内容
中文总结 AI 辅助
通过心理测量问卷评估LLM人格时，发现人格表达包含聚合特征（大五人格分数）和几何特征（SPD流形）两种可分离成分，其中几何特征并非内在属性，而是框架依赖的协调模式，揭示了LLM人格的双重性质。
中文摘要 AI 辅助
通过心理测量问卷评估LLM人格通常依赖于聚合分数，忽略了实例内相关结构。我们测试这种几何结构是内在的还是框架依赖的。从IPIP-50响应构建实例内相关矩阵，我们在GPT-4o模拟美国人和华裔美国人人格时，在操纵问题顺序下分析SPD流形上的几何结构。我们发现人格表达包含两种可分离成分：聚合特征（大五人格分数）在随机化下下降（21%），但框架鲁棒；几何特征（SPD流形）在框架错位下崩溃（42%下降），但在共享框架下大幅恢复（至84%），超过聚合特征（76%）。这种崩溃-恢复模式揭示了人格几何不是内在的，而是框架依赖的协调模式，编码了聚合不可见的信息。我们的发现建立了LLM人格的双重性质框架——框架依赖的几何与框架鲁棒的聚合——需要框架感知评估，并挑战静态特质概念。
英文摘要
Language models prompted with cultural personas increasingly stand in for human respondents in cross-cultural research. Their responses separate personas cleanly, and that separation is read as evidence of a cultural point of view. We show that the separation is real, that the point of view is not, and that one criterion tells them apart. A trait is structure internal to one respondent that survives a change of measurement frame; a bias needs only group-specific item means. To test for the first, we represent a single response set as an Item--Dimension matrix and treat its correlation matrix as a point on the manifold of symmetric positive definite matrices. In humans this carries what a trait should: it reproduces across test--retest sessions sharing no items, order or context ($r=0.77$, $N=89$); on public NEO-PI-R data it identifies individuals at up to $76\%$ against a $0.4\%$ chance level ($N=263$); and it predicts GPA ($R^2=0.281$, $p=0.003$) where BigFive aggregates from the same responses predict nothing ($R^2=0.018$). In four frontier LLMs it returns nothing. Persona structure is readable only while every instance shares one item order: give each its own order and separation falls from $94.7\%$ to chance, while realigning instances to \emph{any} shared random order restores it to $82$--$84\%$. Responses generated independently item by item, with no latent structure, reproduce the entire pattern. The cultural signal is a group template, not a property of any instance, and alignment regimes differ only in which stereotype survives on the surface.
