Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity
Human preference plays a crucial role in the refinement of large language models (LLMs). However, collecting human preference feedback is costly and most existing datasets neglect the correlation between personalization and preferences. To address this issue, we introduce Fair-PP, a synthetic dataset of personalized preferences targeting social equity, derived from real-world social survey data, which includes 28 social groups, 98 equity topics, and 5 personal preference dimensions. Leveraging GPT-4o-mini, we engage in role-playing based on seven representative persona portrayals guided by existing social survey data, yielding a total of 238,623 preference records. Through Fair-PP, we also contribute (i) An automated framework for generating preference data, along with a more fine-grained dataset of personalized preferences; (ii) analysis of the positioning of the existing mainstream LLMs across five major global regions within the personalized preference space; and (iii) a sample reweighting method for personalized preference alignment, enabling alignment with a target persona while maximizing the divergence from other personas. Empirical experiments show our method outperforms the baselines.
Code (1)
Tasks
SurveySimilar Papers 제목 키워드 기반
PAD: Personalized Alignment of LLMs at Decoding-Time
Aligning with personalized preferences, which vary significantly across cultural, educational, and political differences, poses a significant challenge due to the computational costs and data demands of traditional align…
Text GenerationPersonalized Counterfactual Fairness in Recommendation
Recommender systems are gaining increasing and critical impacts on human and society since a growing number of users use them for information seeking and decision making. Therefore, it is crucial to address the potential…
counterfactualDecision MakingFairnessRecommendation SystemsPersonalized Language Modeling from Personalized Human Feedback
Personalized large language models (LLMs) are designed to tailor responses to individual user preferences. While Reinforcement Learning from Human Feedback (RLHF) is a commonly used framework for aligning LLMs with human…
Instruction FollowingLanguage ModelingLanguage ModellingPreference Mapping+1AlignGroup: Learning and Aligning Group Consensus with Member Preferences for Group Recommendation
Group activities are important behaviors in human society, providing personalized recommendations for groups is referred to as the group recommendation task. Existing methods can usually be categorized into two strategie…
Decision MakingMAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment
Personalized product search aims to retrieve and rank items that match users' preferences and search intent. Despite their effectiveness, existing approaches typically assume that users' query fully captures their real m…
Contrastive Learning