Metraipolis › archive › dc_986ffcf04b72

Does Every User Need a Private LoRA? Decoupling Personalization from Per-User Adaptation — arXiv:2610.02353

Source
arXiv
Original
https://arxiv.org/abs/2610.02353
License (as archived)
CC0-1.0
Archived
2026-10-05T22:51:52.513Z
SHA-256 of the archived text
70a903ddb221f0ddedf17e33f64497afe745db69ad6ae2b5a0584923fab9675f
Stable URL of this page
https://metraipolis.com/documento/dc_986ffcf04b72

How to cite

Does Every User Need a Private LoRA? Decoupling Personalization from Per-User Adaptation — arXiv:2610.02353 — arXiv, https://arxiv.org/abs/2610.02353 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_986ffcf04b72 (Metraipolis archive dc_986ffcf04b72, sha256 70a903ddb221f0ddedf17e33f64497afe745db69ad6ae2b5a0584923fab9675f)
BibTeX
@misc{dc986ffcf04b72,
  title = {Does Every User Need a Private LoRA? Decoupling Personalization from Per-User Adaptation — arXiv:2610.02353},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02353},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_986ffcf04b72; sha256 70a903ddb221f0ddedf17e33f64497afe745db69ad6ae2b5a0584923fab9675f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02353. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 propose LINEUP. It learns a bank of reusable low-rank personalization factors, composes them through user-conditioned recall and query-dependent calibration, and restricts target-user adaptation to a tiny user code over a shared correction space. This design decouples expressive personalization capacity from per-user trainable state. Each target user optimizes only eight scalars, while all shared components remain fixed. By comparison, the evaluated private-LoRA configuration uses 4.19 million per-user parameters. Our theoretical analysis gives a finite-step, finite-history risk bound and sufficient conditions for user-code refinement to improve on history initialization. Across six tasks spanning personalized classification, prediction, and generation, LINEUP leads on all 12 metrics, each averaged over three independent runs (e.g., reducing LaMP-3 RMSE by 11.4% relative to the strongest baseline). It maintains advantages under limited history. These results show that rich personalization can be supported primarily by reusable, conditionally composed shared capacity, while independent user adaptation remains confined to a tiny correction state.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.02353 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-05T22:46:10.602Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).