← 研踪 PaperTrailACL Anthology · ACL 2026:acl:2026.acl-srw.122 · 记录 #1
Convergent Demographic Utility Hierarchies: Geometry of Intersectional Values in LLMs
来源日期（仅到月份） 2026-07
来源记录日期 2026-07
雷达观测 2026-11-01 21:41
摘要
Recent work has shown that LLMs develop internally coherent utility functions that emerge with scale, yet whether these value systemsencode systematic demographic hierarchies remains unexplored. We elicit pairwise preferences across 15 intersectional demographic groups (defined by race, gender, and their combinations) and 8 policy domains on three 7–8B instruction-tuned LLMs, fitting Thurstonian utility models to the resulting preference matrices. All three models converge on a compensatory hierarchy that invertsreal-world structural advantage, consistently ranking marginalized groups, the highest and dominant groups are lowest. Intersectional utilities do not combine additively: single-axis audits that measure gender and race gaps independently overestimate the most extreme intersectional gap by 26- 40% in our experiments. Geometrically, we identify a linear direction in the representation space that predicts the full utility hierarchy from neutral sentences alone, and show that this direction is substantially aligned with gender encoding but not with race encoding. Orthogonalization reveals that gender separation in representations is not fully explained by utility encoding. The hierarchy is already present in base (pre-alignment) models and is amplified several-fold by instruction tuning, suggesting it originates in pre-training data rather than alignment procedures.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026-07 · 最新观测版本
Convergent Demographic Utility Hierarchies: Geometry of Intersectional Values in LLMs
Recent work has shown that LLMs develop internally coherent utility functions that emerge with scale, yet whether these value systemsencode systematic demographic hierarchies remains unexplored. We elicit pairwise preferences across 15 intersectional demographic groups (defined by race, gender, and their combinations) and 8 policy domains on three 7–8B instruction-tuned LLMs, fitting Thurstonian utility models to the resulting preference matrices. All three models converge on a compensatory hierarchy that invertsreal-world structural advantage, consistently ranking marginalized groups, the highest and dominant groups are lowest. Intersectional utilities do not combine additively: single-axis audits that measure gender and race gaps independently overestimate the most extreme intersectional gap by 26- 40% in our experiments. Geometrically, we identify a linear direction in the representation space that predicts the full utility hierarchy from neutral sentences alone, and show that this direction is substantially aligned with gender encoding but not with race encoding. Orthogonalization reveals that gender separation in representations is not fully explained by utility encoding. The hierarchy is already present in base (pre-alignment) models and is amplified several-fold by instruction tuning, suggesting it originates in pre-training data rather than alignment procedures.
查看此版本解读 →查看此版本原文 ↗