通过隐空间建模用户差异，让大模型更懂每个人的表达习惯。
Latent Inter-User Difference Modeling for LLM Personalization
- 在隐空间对比用户与相似行为者，生成差异感知的软提示。
- 在多个指标上优于基线方法，个性化生成效果更佳。
- 适合需要精准用户个性化的场景，如智能客服、内容创作。
大型语言模型日益融入用户日常生活，对个性化输出的需求持续增长。以往研究多依赖用户自身历史，忽视了用户间差异这一关键因素。尽管近期工作尝试建模此类差异，但依赖语言提示常阻碍有效区分特征的提取。为此，我们提出差异感知嵌入式个性化框架（DEP），不再依赖语言提示，而是在隐空间中建模用户间差异。DEP通过对比用户嵌入与其同类用户（共同参与相似内容）的嵌入，构建软提示，突出相对行为信号。随后，稀疏自编码器过滤并压缩用户特定及差异感知嵌入，仅保留任务相关特征后注入冻结的LLM。在个性化评论生成任务上的实验表明，DEP在多个指标上持续优于基线方法。代码已开源：https://github.com/SnowCharmQ/DEP。
原文摘要 · Abstract (English)
Large language models (LLMs) are increasingly integrated into users' daily lives, leading to a growing demand for personalized outputs. Previous work focuses on leveraging a user's own history, overlooking inter-user differences that are crucial for effective personalization. While recent work has attempted to model such differences, the reliance on language-based prompts often hampers the effective extraction of meaningful distinctions. To address these issues, we propose Difference-aware Embedding-based Personalization (DEP), a framework that models inter-user differences in the latent space instead of relying on language prompts. DEP constructs soft prompts by contrasting a user's embedding with those of peers who engaged with similar content, highlighting relative behavioral signals. A sparse autoencoder then filters and compresses both user-specific and difference-aware embeddings, preserving only task-relevant features before injecting them into a frozen LLM. Experiments on personalized review generation show that DEP consistently outperforms baseline methods across multiple metrics. Our code is available at https://github.com/SnowCharmQ/DEP.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。