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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Linhai, Wu, Jialong, Zhou, Deyu, He, Yulan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913715307151360
author Zhang, Linhai
Wu, Jialong
Zhou, Deyu
He, Yulan
author_facet Zhang, Linhai
Wu, Jialong
Zhou, Deyu
He, Yulan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_01303
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation
Zhang, Linhai
Wu, Jialong
Zhou, Deyu
He, Yulan
Computation and Language
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.
title PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation
topic Computation and Language
url https://arxiv.org/abs/2503.01303