PersonaEdit：用于个性化模型编辑的代表性样本选择

中文摘要 AI 辅助

个性化在大语言模型（LLM）应用中已受到越来越多的关注，但现有的基于检索的方法严重依赖检索质量，且在长期交互中性能会下降。模型编辑是指直接修改模型内部参数以融入新知识，已在事实知识编辑任务中展现出有效的知识修改能力，可能为个性化提供潜在解决方案。然而，将模型编辑扩展到个性化场景并非易事：编辑大量用户数据会增加计算成本，并导致编辑之间相互干扰，因此需要有效的样本选择策略来解决该问题。为此，我们提出了PersonaEdit，一种隐藏表示聚类策略，通过比例分层采样选择代表性编辑样本。实验表明，模型编辑对个性化是有效的，且我们的选择策略在保留大部分性能的同时大幅减少了所需的编辑样本数量。除单独使用编辑外，我们还发现将模型编辑与基于检索的提示增强相结合可进一步提升个性化效果，因为编辑后的知识和检索到的上下文提供了互补信息。这些结果证明了模型编辑作为一种高效且可扩展的LLM个性化方法的潜力。

英文摘要

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.

发表机构

• National Yang Ming Chiao Tung University（国立阳明交通大学）
• National Institute of Informatics（信息学研究所）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

Accepted by EMNLP 2026 Findings