האם כל משתמש צריך LoRA פרטי? פרידה בין התאמה אישית להתאמה נפרדת לכל משתמש

תקציר מקורי באנגליתarXiv:2610.02353v1 Announce Type: new Abstract: Personalized large language models often require a complete adaptation state for each user. However, this paradigm scales poorly as the user population grows. We revisit this design through the lens of personalization capacity allocation: how much adaptation capacity can be shared across users, how the shared capacity should be composed, and how much must remain user-specific. We answer them through three complementary empirical analyses. We find that independent user adapters contain substantial cross-user reusable structure, that the utility of reusable directions reflects both user relevance and variation across queries, and that user histories provide transferable signals for compact individual correction. Motivated by these findings, we