# PersonaEdit: Representative Sample Selection for Personalized Model Editing

arXiv: https://arxiv.org/abs/2608.27816 · HTML: https://mlsanity.com/paper/2608.27816/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Model Editing at Scale leads to Gradual and Catastrophic Forgetting](https://mlsanity.com/paper/2401.07453/) (2024)
- [Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization](https://mlsanity.com/paper/2503.02450/) (2025)
- [Few-shot Personalization of LLMs with Mis-aligned Responses](https://mlsanity.com/paper/2406.18678/) (2024)
- [LLMs + Persona-Plug = Personalized LLMs](https://mlsanity.com/paper/2409.11901/) (2024)
- [User Embedding Model for Personalized Language Prompting](https://mlsanity.com/paper/2401.04858/) (2024)
- [Latent Inter-User Difference Modeling for LLM Personalization](https://mlsanity.com/paper/2507.20849/) (2025)
- [Personalize Your LLM: Fake it then Align it](https://mlsanity.com/paper/2503.01048/) (2025)
- [Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval](https://mlsanity.com/paper/2510.08935/) (2025)
- [An Effectiveness Metric for Ordinal Classification: Formal Properties and Experimental Results](https://mlsanity.com/paper/2006.01245/) (2020)
- [MEMIT-Merge: Addressing MEMIT's Key-Value Conflicts in Same-Subject Batch Editing for LLMs](https://mlsanity.com/paper/2502.07322/) (2025)
- [Towards Effective Model Editing for LLM Personalization](https://mlsanity.com/paper/2512.13676/) (2025)

## Abstract (arXiv)

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.