作者位次 #5/7ACL 2026Findings· Findings of ACL
From Personal to Collective: On the Role of Local and Global Knowledge in LLM Personalization
Zehong Wang · Junlin Wu · Zhaoxuan Tan · Bolian Li · Xianrui Zhong · Zheli Liu · Qingkai Zeng
摘要
Large language model (LLM) personalization typically relies on modeling each user in isolation, conditioning on their historical interactions to adapt model behavior. However, this user-centric formulation overlooks the collective knowledge shared across users, limiting generalization for users w...