用人格特质筛选偏好，让大模型回答更符合用户真实喜好。
PACIFIC: Can LLMs Discern the Traits Influencing Your Preferences? Evaluating Personality-Driven Preference Alignment in LLMs
- 以人格特质为隐变量筛选用户偏好，提升个性化回答准确性。
- 匹配人格的偏好使回答准确率从29.25%提升至76%。
- 构建了带五大性格标签的1200条偏好数据集，适合做个性化的研究者使用。
用户偏好被广泛用于个性化大语言模型（LLM）响应，但如何可靠利用偏好信号生成答案仍缺乏深入探索。实践中，偏好常存在噪声、不完整或误导性，若盲目使用会降低回答质量。受稳定人格特质影响日常偏好的观察启发，本文将人格视为偏好背后的结构性‘潜变量’。通过大量实验发现，基于人格一致性的偏好选择可显著提升个性化问答表现：与随机选择偏好相比，匹配用户推断人格的偏好使答案选择准确率从29.25%提升至76%。基于此，我们提出PACIFIC（Preference Alignment Choices Inference for Five-factor Identity Characterization），一个包含1200条跨领域（如旅行、电影、教育）偏好陈述的人格标注数据集，每条均标注了五大性格（OCEAN）方向。最后，我们设计了一套框架，使大模型能自动检索并融合人格对齐的偏好进行生成。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。