MTA: A Merge-then-Adapt Framework for Personalized Large Language Model
By: Xiaopeng Li , Yuanjin Zheng , Wanyu Wang and more
Potential Business Impact:
Makes AI understand *your* needs better, cheaper.
Personalized Large Language Models (PLLMs) aim to align model outputs with individual user preferences, a crucial capability for user-centric applications. However, the prevalent approach of fine-tuning a separate module for each user faces two major limitations: (1) storage costs scale linearly with the number of users, rendering the method unscalable; and (2) fine-tuning a static model from scratch often yields suboptimal performance for users with sparse data. To address these challenges, we propose MTA, a Merge-then-Adapt framework for PLLMs. MTA comprises three key stages. First, we construct a shared Meta-LoRA Bank by selecting anchor users and pre-training meta-personalization traits within meta-LoRA modules. Second, to ensure scalability and enable dynamic personalization combination beyond static models, we introduce an Adaptive LoRA Fusion stage. This stage retrieves and dynamically merges the most relevant anchor meta-LoRAs to synthesize a user-specific one, thereby eliminating the need for user-specific storage and supporting more flexible personalization. Third, we propose a LoRA Stacking for Few-Shot Personalization stage, which applies an additional ultra-low-rank, lightweight LoRA module on top of the merged LoRA. Fine-tuning this module enables effective personalization under few-shot settings. Extensive experiments on the LaMP benchmark demonstrate that our approach outperforms existing SOTA methods across multiple tasks.
Similar Papers
MTA: A Merge-then-Adapt Framework for Personalized Large Language Model
Computation and Language
Makes AI understand *your* needs better, cheaper.
MeTA-LoRA: Data-Efficient Multi-Task Fine-Tuning for Large Language Models
Computation and Language
Teaches AI more with less information.
Efficient Knowledge Transfer in Multi-Task Learning through Task-Adaptive Low-Rank Representation
Computation and Language
Teaches AI new jobs without retraining it.