{"ID":2889646,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.20849","arxiv_id":"2507.20849","title":"Latent Inter-User Difference Modeling for LLM Personalization","abstract":"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.","short_abstract":"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 su...","url_abs":"https://arxiv.org/abs/2507.20849","url_pdf":"https://arxiv.org/pdf/2507.20849v2","authors":"[\"Yilun Qiu\",\"Tianhao Shi\",\"Xiaoyan Zhao\",\"Fengbin Zhu\",\"Yang Zhang\",\"Fuli Feng\"]","published":"2025-07-28T14:00:57Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":611670,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2889646,"paper_url":"https://arxiv.org/abs/2507.20849","paper_title":"Latent Inter-User Difference Modeling for LLM Personalization","repo_url":"https://github.com/SnowCharmQ/DEP","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}