PersonaEdit: Representative Sample Selection for Personalized Model Editing

[2608.27816] PersonaEdit: Representative Sample Selection for Personalized Model Editing Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2608.27816 (cs) [Submitted on 28 Aug 2026] Title: PersonaEdit: Representative Sample Selection for Personalized Model Editing Authors: You-Mei Huang , Chung-Chi Chen , An-Zi Yen View PDF HTML (experimental) Abstract: 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. Comments: Accepted by EMNLP 2026 Findings Subjects: Computation and Language (cs.CL) Cite as: arXiv:2608.27816 [cs.CL] (or arXiv:2608.27816v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2608.27816 Focus to learn more arXiv-issued DOI via DataCite Submission history From: An-Zi Yen [ view email ] [v1] Fri, 28 Aug 2026 01:25:29 UTC (874 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CL < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• PersonaEdit: Representative Sample Selection for Personalized Model Editing#779731
• Show Me Your Prompts! How Writers Feel About Sharing Prompts in Collaborative Text Editors#1083885
• WildSEEK: Evaluating Language Models for Information-Seeking#818738
• WildSEEK: Evaluating Language Models for Information-Seeking#808746
• Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs#997322