文本作为通用的可转移个性化接口
Text as a Universal Interface for Transferable Personalization
AI总结：
本文提出利用自然语言作为通用接口，通过两阶段训练框架开发出可转移的偏好推理模型，实现在多个任务和模型家族中的高性能表现。
摘要：
我们研究了大型语言模型（LLMs）中的个性化问题。先前的工作大多将用户偏好表示为隐含的、模型特定的向量或参数，导致不透明的「黑箱」配置文件，难以在不同模型和任务之间解释和转移。相反，我们倡导自然语言作为通用的、与模型和任务无关的偏好表示接口。该方法导致可解释且可重用的偏好描述，同时自然支持持续进化，随着新交互的观察而不断更新。为了学习此类表示，我们引入了一个两阶段训练框架，结合在高质量合成数据上的监督微调与强化学习，以优化长期效用和跨任务可转移性。基于此框架，我们开发了AlignXplore+，一个通用的偏好推理模型，能够生成文本偏好摘要。在九个基准测试中，我们的8B模型实现了最先进的性能——远超大幅更大的开源模型——同时在任务、模型家族和交互格式之间表现出强大的可转移性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
