从个人到集体：论局部与全局记忆在 LLM 个性化中的作用
From Personal to Collective: On the Role of Local and Global Memory in LLM Personalization
AI总结：
针对 LLM 个性化中的冷启动与历史偏置问题，本文提出 LoGo 局部—全局记忆框架及冲突中介模块，利用跨用户集体知识提升个性化效果。
摘要：
大语言模型（LLM）个性化旨在根据用户的历史交互，使模型行为适配个体用户。然而，其有效性常受到两个关键挑战的阻碍：冷启动问题，即历史有限的用户无法提供足够上下文以实现准确个性化；以及偏置问题，即拥有丰富但偏斜历史的用户会使模型过拟合于狭窄偏好。我们将这两个问题识别为同一潜在局限的表现，即无法对跨用户的集体知识进行建模。为解决该问题，我们提出一种局部—全局记忆框架（LoGo），将个性化局部记忆与捕捉人群共享兴趣的集体全局记忆相结合。为协调这两种记忆来源之间的差异，我们引入了一个中介模块，用于解决局部与全局信号之间的冲突。在多个基准上进行的大量实验表明，LoGo 持续提升个性化质量，既为冷启动用户完成预热，也缓解了有偏预测。这些结果凸显了纳入集体知识以增强 LLM 个性化的重要性。
英文摘要：
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.
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。
