PACIFIC: Can LLMs Discern the Traits Influencing Your Preferences? Evaluating Personality-Driven Preference Alignment in LLMs

TL;DR

This paper investigates how personality traits influence user preferences and demonstrates that aligning preferences with inferred personality traits significantly improves LLM response accuracy.

Contribution

The study introduces PACIFIC, a new dataset of personality-labeled preferences, and proposes a framework for LLMs to automatically incorporate personality-aligned preferences.

Findings

Aligning preferences with personality traits increases answer accuracy from 29.25% to 76%.

Introducing the PACIFIC dataset with 1200 personality-annotated preferences.

Proposed framework enables LLMs to retrieve and incorporate personality-aligned preferences.

Abstract

User preferences are increasingly used to personalize Large Language Model (LLM) responses, yet how to reliably leverage preference signals for answer generation remains under-explored. In practice, preferences can be noisy, incomplete, or even misleading, which can degrade answer quality when applied naively. Motivated by the observation that stable personality traits shape everyday preferences, we study personality as a principled ''latent'' signal behind preference statements. Through extensive experiments, we find that conditioning on personality-aligned preferences substantially improves personalized question answering: selecting preferences consistent with a user's inferred personality increases answer-choice accuracy from 29.25% to 76%, compared to using randomly selected preferences. Based on these findings, we introduce PACIFIC (Preference Alignment Choices Inference for Five-factor Identity Characterization), a personality-labeled preference dataset containing 1200 preference statements spanning diverse domains (e.g., travel, movies, education), annotated with Big-Five (OCEAN) trait directions. Finally, we propose a framework that enables an LLM model to automatically retrieve personality-aligned preferences and incorporate them during answer generation.