Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.04963 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908753942544384 |
|---|---|
| author | Liu, Yuting Guan, Jian Li, Jia-Nan Wu, Wei Yang, Jiang-Ming Zhao, Jianzhe Guo, Guibing |
| author_facet | Liu, Yuting Guan, Jian Li, Jia-Nan Wu, Wei Yang, Jiang-Ming Zhao, Jianzhe Guo, Guibing |
| contents | We study the problem of personalization in large language models (LLMs). Prior work predominantly represents user preferences as implicit, model-specific vectors or parameters, yielding opaque ``black-box'' profiles that are difficult to interpret and transfer across models and tasks. In contrast, we advocate natural language as a universal, model- and task-agnostic interface for preference representation. The formulation leads to interpretable and reusable preference descriptions, while naturally supporting continual evolution as new interactions are observed. To learn such representations, we introduce a two-stage training framework that combines supervised fine-tuning on high-quality synthesized data with reinforcement learning to optimize long-term utility and cross-task transferability. Based on this framework, we develop AlignXplore+, a universal preference reasoning model that generates textual preference summaries. Experiments on nine benchmarks show that our 8B model achieves state-of-the-art performanc -- outperforming substantially larger open-source models -- while exhibiting strong transferability across tasks, model families, and interaction formats. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04963 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Text as a Universal Interface for Transferable Personalization Liu, Yuting Guan, Jian Li, Jia-Nan Wu, Wei Yang, Jiang-Ming Zhao, Jianzhe Guo, Guibing Computation and Language Artificial Intelligence We study the problem of personalization in large language models (LLMs). Prior work predominantly represents user preferences as implicit, model-specific vectors or parameters, yielding opaque ``black-box'' profiles that are difficult to interpret and transfer across models and tasks. In contrast, we advocate natural language as a universal, model- and task-agnostic interface for preference representation. The formulation leads to interpretable and reusable preference descriptions, while naturally supporting continual evolution as new interactions are observed. To learn such representations, we introduce a two-stage training framework that combines supervised fine-tuning on high-quality synthesized data with reinforcement learning to optimize long-term utility and cross-task transferability. Based on this framework, we develop AlignXplore+, a universal preference reasoning model that generates textual preference summaries. Experiments on nine benchmarks show that our 8B model achieves state-of-the-art performanc -- outperforming substantially larger open-source models -- while exhibiting strong transferability across tasks, model families, and interaction formats. |
| title | Text as a Universal Interface for Transferable Personalization |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.04963 |