Researchllmsocial preferencesstructural estimationsequential decision making
LLMs Exhibit Malleable Social And Temporal Preferences
9.3
Relevance Score
Thomas R. Cook, Sophia Kazinnik, Zach Modig, and Nathan M. Palmer (January 2026) analyze latent preferences of large language models using dictator-style allocation games and a sequential McCall job-search environment. They find models often favor equal splits—suggesting stronger inequality aversion than humans—and show prompt framing and control vectors can steer models toward payoff-maximizing behavior, though steering is less reliable in complex, dynamic tasks.
