5 papers
Gradient-Aligned Pair Selection for Personalized Preference Optimization
Ruoming Jin, Xinyu Li, Hao Zhou +6
Personalizing large language models (LLMs) requires aligning generation behavior with user-specific preferences rather than aggregate quality. While Direct Preference Optimization…
Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM
Xinyu Li, Ruoming Jin, Jianfeng Zhu +2
In this paper, we study the problem of personalized survey response prediction using fine-tuned large language models (LLMs). This task poses unique challenges: limited per-user tr…
PLUME: Parameter-Efficient Personalization of Large Language Models via Low-Rank User Modulation in Shared Subspaces
Xinyu Li, Hao Zhou, Jianfeng Zhu +4
Personalizing large language models (LLMs) is essential for delivering AI assistance that aligns with individual users' styles, intents, and preferences. While per-user fine-tuning…
Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic Loss
Ruixin Guo, Xinyu Li, Hao Zhou +2
Linear autoencoders (LAEs) have gained increasing popularity in recommender systems due to their simplicity and strong empirical performance. Most LAE models, including the Emphasi…
PAC-Bayes Bounds for Multivariate Linear Regression and Linear Autoencoders
Ruixin Guo, Ruoming Jin, Xinyu Li +1
Linear Autoencoders (LAEs) have shown strong performance in state-of-the-art recommender systems. However, this success remains largely empirical, with limited theoretical understa…