PLUME: Parameter-Efficient Personalization of Large Language Models via Low-Rank User Modulation in Shared Subspaces
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 can substantially enhance personalization quality, it introduces significant parameter and storage overhead, limiting scalability to large u...
Xin-Yu Li, Hao Zhou, Jian-Feng Zhu et al.
· 0 citations