Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.23767 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909813034713088 |
|---|---|
| author | Wang, Zehong Wu, Junlin Tan, ZHaoxuan Li, Bolian Zhong, Xianrui Liu, Zheli Zeng, Qingkai |
| author_facet | Wang, Zehong Wu, Junlin Tan, ZHaoxuan Li, Bolian Zhong, Xianrui Liu, Zheli Zeng, Qingkai |
| contents | Large language model (LLM) personalization aims to tailor model behavior to individual users based on their historical interactions. However, its effectiveness is often hindered by two key challenges: the \textit{cold-start problem}, where users with limited history provide insufficient context for accurate personalization, and the \textit{biasing problem}, where users with abundant but skewed history cause the model to overfit to narrow preferences. We identify both issues as symptoms of a common underlying limitation, i.e., the inability to model collective knowledge across users. To address this, we propose a local-global memory framework (LoGo) that combines the personalized local memory with a collective global memory that captures shared interests across the population. To reconcile discrepancies between these two memory sources, we introduce a mediator module designed to resolve conflicts between local and global signals. Extensive experiments on multiple benchmarks demonstrate that LoGo consistently improves personalization quality by both warming up cold-start users and mitigating biased predictions. These results highlight the importance of incorporating collective knowledge to enhance LLM personalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23767 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Personal to Collective: On the Role of Local and Global Memory in LLM Personalization Wang, Zehong Wu, Junlin Tan, ZHaoxuan Li, Bolian Zhong, Xianrui Liu, Zheli Zeng, Qingkai Computation and Language Artificial Intelligence Large language model (LLM) personalization aims to tailor model behavior to individual users based on their historical interactions. However, its effectiveness is often hindered by two key challenges: the \textit{cold-start problem}, where users with limited history provide insufficient context for accurate personalization, and the \textit{biasing problem}, where users with abundant but skewed history cause the model to overfit to narrow preferences. We identify both issues as symptoms of a common underlying limitation, i.e., the inability to model collective knowledge across users. To address this, we propose a local-global memory framework (LoGo) that combines the personalized local memory with a collective global memory that captures shared interests across the population. To reconcile discrepancies between these two memory sources, we introduce a mediator module designed to resolve conflicts between local and global signals. Extensive experiments on multiple benchmarks demonstrate that LoGo consistently improves personalization quality by both warming up cold-start users and mitigating biased predictions. These results highlight the importance of incorporating collective knowledge to enhance LLM personalization. |
| title | From Personal to Collective: On the Role of Local and Global Memory in LLM Personalization |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2509.23767 |