Towards Effective Model Editing for LLM Personalization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914202066616320 |
|---|---|
| author | Huang, Baixiang Cui, Limeng Liu, Jiapeng Wang, Haoran Xu, Jiawei Tan, Zhuiyue Chen, Yutong Luo, Chen Liu, Yi Shu, Kai |
| author_facet | Huang, Baixiang Cui, Limeng Liu, Jiapeng Wang, Haoran Xu, Jiawei Tan, Zhuiyue Chen, Yutong Luo, Chen Liu, Yi Shu, Kai |
| contents | Personalization is becoming indispensable for LLMs to align with individual user preferences and needs. Yet current approaches are often computationally expensive, data-intensive, susceptible to catastrophic forgetting, and prone to performance degradation in multi-turn interactions or when handling implicit queries. To address these challenges, we conceptualize personalization as a model editing task and introduce Personalization Editing, a framework that applies localized edits guided by clustered preference representations. This design enables precise preference-aligned updates while preserving overall model capabilities. In addition, existing personalization benchmarks frequently rely on persona-based dialogs between LLMs rather than user-LLM interactions, or focus primarily on stylistic imitation while neglecting information-seeking tasks that require accurate recall of user-specific preferences. We introduce User Preference Question Answering (UPQA), a short-answer QA dataset constructed from in-situ user queries with varying levels of difficulty. Unlike prior benchmarks, UPQA directly evaluates a model's ability to recall and apply specific user preferences. Across experimental settings, Personalization Editing achieves higher editing accuracy and greater computational efficiency than fine-tuning, while outperforming prompting-based baselines in multi-turn conversations and implicit preference questions settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_13676 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Effective Model Editing for LLM Personalization Huang, Baixiang Cui, Limeng Liu, Jiapeng Wang, Haoran Xu, Jiawei Tan, Zhuiyue Chen, Yutong Luo, Chen Liu, Yi Shu, Kai Computation and Language Personalization is becoming indispensable for LLMs to align with individual user preferences and needs. Yet current approaches are often computationally expensive, data-intensive, susceptible to catastrophic forgetting, and prone to performance degradation in multi-turn interactions or when handling implicit queries. To address these challenges, we conceptualize personalization as a model editing task and introduce Personalization Editing, a framework that applies localized edits guided by clustered preference representations. This design enables precise preference-aligned updates while preserving overall model capabilities. In addition, existing personalization benchmarks frequently rely on persona-based dialogs between LLMs rather than user-LLM interactions, or focus primarily on stylistic imitation while neglecting information-seeking tasks that require accurate recall of user-specific preferences. We introduce User Preference Question Answering (UPQA), a short-answer QA dataset constructed from in-situ user queries with varying levels of difficulty. Unlike prior benchmarks, UPQA directly evaluates a model's ability to recall and apply specific user preferences. Across experimental settings, Personalization Editing achieves higher editing accuracy and greater computational efficiency than fine-tuning, while outperforming prompting-based baselines in multi-turn conversations and implicit preference questions settings. |
| title | Towards Effective Model Editing for LLM Personalization |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2512.13676 |