PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation

TY - CONF

T1 - PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation

AU - Zhang, Linhai

AU - Wu, Jialong

AU - Zhou, Deyu

AU - He, Yulan

PY - 2025/5/15

Y1 - 2025/5/15

N2 - Personalized large language models (LLMs) aim to tailor their outputs to user preferences. Recent advances in parameter-efficient fine-tuning (PEFT) methods have highlighted the effectiveness of adapting population-level LLMs to personalized LLMs by fine-tuning user-specific parameters with user history. However, user data is typically sparse, making it challenging to adapt LLMs to specific user patterns. To address this challenge, we propose PROgressive PERsonalization (PROPER), a novel progressive learning framework inspired by meso-level theory in social science. PROPER bridges population-level and user-level models by grouping users based on preferences and adapting LLMs in stages. It combines a Mixture-of-Experts (MoE) structure with Low Ranked Adaptation (LoRA), using a user-aware router to assign users to appropriate groups automatically. Additionally, a LoRA-aware router is proposed to facilitate the integration of individual user LoRAs with group-level LoRAs. Experimental results show that PROPER significantly outperforms SOTA models across multiple tasks, demonstrating the effectiveness of our approach. Our code is available at https://github.com/callanwu/PROPER.

AB - Personalized large language models (LLMs) aim to tailor their outputs to user preferences. Recent advances in parameter-efficient fine-tuning (PEFT) methods have highlighted the effectiveness of adapting population-level LLMs to personalized LLMs by fine-tuning user-specific parameters with user history. However, user data is typically sparse, making it challenging to adapt LLMs to specific user patterns. To address this challenge, we propose PROgressive PERsonalization (PROPER), a novel progressive learning framework inspired by meso-level theory in social science. PROPER bridges population-level and user-level models by grouping users based on preferences and adapting LLMs in stages. It combines a Mixture-of-Experts (MoE) structure with Low Ranked Adaptation (LoRA), using a user-aware router to assign users to appropriate groups automatically. Additionally, a LoRA-aware router is proposed to facilitate the integration of individual user LoRAs with group-level LoRAs. Experimental results show that PROPER significantly outperforms SOTA models across multiple tasks, demonstrating the effectiveness of our approach. Our code is available at https://github.com/callanwu/PROPER.

KW - Large Language Models

KW - Personalization

KW - Parameter-Efficient Fine-Tuning

KW - Mixture of Experts

UR - https://arxiv.org/abs/2503.01303

M3 - Paper

T2 - The 63rd Annual Meeting of the Association for Computational Linguistics

Y2 - 27 July 2025 through 1 August 2025

ER -