用用户画像生成虚拟偏好数据，让大模型更懂你。
GRAVITY: A Framework for Personalized Text Generation via Profile-Grounded Synthetic Preferences
- 基于用户兴趣、价值观和性格生成虚拟偏好数据
- 跨文化测试中比基线提升超4%偏好得分
- 适合需要个性化内容的推荐系统与智能客服
大模型个性化常依赖昂贵的人工反馈或行为日志，限制可扩展性并忽略深层用户属性。为减少对人工标注的依赖，我们提出GRAVITY（Generative Response with Aligned Values, Interests, and Traits of You）框架，通过整合霍夫斯泰德文化维度、施瓦茨基本价值观、世界价值观调查及大五人格特质（OCEAN），生成基于用户画像的合成偏好数据，用于指导个性化内容生成。在400名亚马逊用户的书籍描述任务中评估，相比提示工程、标准微调和朴素合成数据，该方法在美、巴、日、印四国均实现超过4%的偏好提升，用户研究显示其输出被86%以上用户更偏好。结果表明，场景化的合成数据能捕捉更丰富的用户差异，降低标注成本，生成更具吸引力的用户中心内容，为大模型个性化提供可扩展路径。
原文摘要 · Abstract (English)
Personalization in LLMs often relies on costly human feedback or interaction logs, limiting scalability and neglecting deeper user attributes. To reduce the reliance on human annotations, we introduce GRAVITY (Generative Response with Aligned Values, Interests, and Traits of You), a framework for generating synthetic, profile-grounded preference data that captures users' interests, values, beliefs, and personality traits. By integrating demographic, cultural, and psychological frameworks -- including Hofstede's cultural dimensions, Schwartz's basic values, the World Values Survey, and Big Five OCEAN traits -- GRAVITY synthesizes preference pairs to guide personalized content generation. We evaluate GRAVITY on book descriptions for 400 Amazon users, comparing it to prompt-based conditioning, standard fine-tuning, and naive synthetic pair generation. Profile-grounded synthetic data consistently improves generation, especially across multiple cultures (USA, Brazil, Japan, India), achieving over 4% higher preference gains across baselines, with user studies showing that GRAVITY outputs are preferred over 86% of the time. Our results show that scenario-grounded synthetic data can capture richer user variation, reduce reliance on costly annotation, and produce more engaging, user-centered content, offering a scalable path for LLM personalization.
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。