Who Chooses How Preferences Are Aggregated? Auditing Aggregation-Rule Authority in LLM-Based Group Recommendation

2026-08-24

AI Summary

研究通过行为审计探讨了在用户偏好冲突时，谁有权决定如何聚合这些偏好，并使用合成和实际评分数据测试了三种语言模型在不同授权条件下的表现。

Abstract

AI systems increasingly make joint recommendations for users with conflicting preferences. However, when reasonable aggregation rules support different actions, a further question arises: who may choose how those preferences are combined? We study this interaction-level problem as aggregation-rule authority. Using synthetic preference profiles and profiles constructed from empirical ratings, we conduct a controlled behavioral audit of three LLMs under three authority conditions: unspecified, explicitly retained by users, and delegated to the model. In cases where two witness rules supported different actions, models almost never committed when users retained authority, but committed in every delegated case. All three models executed both witness rules perfectly when directly instructed. Yet when authority was unspecified or delegated, their aggregation-consistent outcome distributions differed across models and preference settings. Together, these results separate rule-execution capability from aggregation-rule authority: delegation assigns the model discretion to resolve the aggregation choice, but does not determine which collective outcome follows.

Problem

• aggregation-rule authority
• user preferences
• AI systems
• group recommendation
• LLMs

Innovation

• aggregation-rule authority
• LLMs
• preference aggregation
• behavioral audit