PACIFIC: Can LLMs Discern the Psychometric Traits Influencing Your Preferences? Personality-Driven Preference Alignment in LLMs
PACIFIC (Preference Alignment for Choices Inference via Five-factor Identity Characterization), a personality-driven preference alignment framework that uses Big-Five (OCEAN) traits as a principled "latent"signal for organizing and reasoning over user preference history, is introduced.
Tianyu Zhao, Siqi Li, Yasser Shoukry et al.
· 0 citations