@inproceedings{bao-etal-2025-customizing,
    title = "Customizing In-context Learning for Dynamic Interest Adaption in {LLM}-based Recommendation",
    author = "Bao, Keqin  and
      Yan, Ming  and
      Zhang, Yang  and
      Zhang, Jizhi  and
      Wang, Wenjie  and
      Feng, Fuli  and
      He, Xiangnan",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.findings-acl.735/",
    pages = "14278--14291",
    ISBN = "979-8-89176-256-5",
    abstract = "Frequently updating Large Language Model (LLM)-based recommender systems to adapt to dynamic user interests{---}as done for traditional ones{---}is impractical due to high training costs, even with acceleration methods. This work explores the possibility of adapting the model to dynamic user interests without any model-level updates via In-context Learning (ICL), which enables adaptation through few-shot examples within input prompts. While using recent user interactions as ICL demonstrations offers a potential solution for dynamic interest adaptation, existing LLM-based recommenders face critical limitations: recommendation-specific tuning often diminishes the model{'}s in-context learning ability, and the original LLM{'}s ICL lacks task-specific optimization for recommendations. To bridge this gap, we introduce RecICL, a framework that establishes recommendation-oriented in-context learning by structuring recent user interactions and current inputs into ICL formats. RecICL achieves dual objectives: (1) preserving fundamental ICL capabilities during recommendation adaptation and (2) dynamically capturing user preference evolution through the most recent interactions. Extensive experiments across multiple benchmarks demonstrate RecICL{'}s superior performance, achieving better results without model updates. Our implementation is publicly available at \url{https://anonymous.4open.science/r/RecICL-8003}."
}