Metraipolis › archive › dc_9060662dd9db
PersonaEdit: Representative Sample Selection for Personalized Model Editing — arXiv:2608.27816
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27816
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T10:56:30.250Z
- SHA-256 of the archived text
4ab0dc0c7359cb406c109b3acf762b3f0341b95516b073b6beba0ff0b04b05c1- Stable URL of this page
https://metraipolis.com/documento/dc_9060662dd9db
How to cite
PersonaEdit: Representative Sample Selection for Personalized Model Editing — arXiv:2608.27816 — arXiv (en), https://arxiv.org/abs/2608.27816 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9060662dd9db (Metraipolis archive dc_9060662dd9db, sha256 4ab0dc0c7359cb406c109b3acf762b3f0341b95516b073b6beba0ff0b04b05c1)
BibTeX
@misc{dc9060662dd9db,
title = {PersonaEdit: Representative Sample Selection for Personalized Model Editing — arXiv:2608.27816},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27816},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9060662dd9db; sha256 4ab0dc0c7359cb406c109b3acf762b3f0341b95516b073b6beba0ff0b04b05c1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27816. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Personalization has attracted growing interest in LLM applications, yet existing retrieval-based approaches depend heavily on retrieval quality and degrade in long-term interactions. Model editing, which directly modifies internal model parameters to incorporate new knowledge, has demonstrated effective knowledge modification capabilities in factual knowledge editing tasks and may provide a potential solution for personalization. However, scaling model editing to personalization is non-trivial. Editing large amounts of user data increases computational cost and causes interference among edits, motivating the need for effective sample selection. To address this issue, we propose, PersonaEdit, a hidden representation clustering strategy that selects representative editing samples through proportional stratified sampling. Experiments show that model editing is effective for personalization, and that our selection strategy preserves most of the performance while substantially reducing the number of required editing samples. Beyond standalone editing, we find that combining model editing with retrieval-based prompt augmentation further improves personalization, as edited knowledge and retrieved context provide complementary information. These results demonstrate the potential of model editing as an efficient and scalable approach for LLM personalization. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.27816 — 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 2026-10-17T10:47:33.113Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).