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

2026-02-06

AI Summary

This work addresses the limitations of existing personalization methods for large language models, which often rely on noisy, incomplete, or misleading user preference signals that degrade response quality. To overcome this, the authors propose leveraging the Big Five personality traits (OCEAN) as a stable latent signal for preference alignment. They first introduce PACIFIC, the first dataset comprising 1,200 personality-annotated preference pairs, and then design an integrated question-answering framework that combines personality inference, preference retrieval, and language model generation to automatically identify and incorporate preferences consistent with the user’s personality. Experimental results demonstrate that this approach significantly improves answer selection accuracy, increasing it from 29.25% under random preferences to 76%, thereby substantially enhancing personalized response quality.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Natural Language Processing: Question Answering
• Humans and AI: Learning Human Values and Preferences

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Web Mining and Content Analysis: Large pretrained models with web data

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.

Problem

• preference alignment
• personality traits
• Large Language Models
• personalized question answering
• noisy preferences

Innovation

• personality-driven preference alignment
• latent preference signal
• Big-Five personality traits
• personalized LLM
• PACIFIC dataset