# Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning

arXiv: https://arxiv.org/abs/2410.23136 · HTML: https://mlsanity.com/paper/2410.23136/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2024.

## Built on by (most cited first, 5 of 5)

- [Prototype-Aligned Federated Soft-Prompts for Continual Web Personalization](https://mlsanity.com/paper/2603.27678/) (2026)
- [Dynamic Retriever for In-Context Knowledge Editing via Policy Optimization](https://mlsanity.com/paper/2510.21059/) (2025)
- [Music Recommendation with Large Language Models: Challenges, Opportunities, and Evaluation](https://mlsanity.com/paper/2511.16478/) (2025)
- [Full-Stack Optimized Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation](https://mlsanity.com/paper/2501.13344/) (2025)
- [GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models](https://mlsanity.com/paper/2607.24764/) (2026)

## Abstract (arXiv)

Frequently updating Large Language Model (LLM)-based recommender systems to adapt to new user interests -- as done for traditional ones -- is impractical due to high training costs, even with acceleration methods. This work explores adapting to dynamic user interests without any model updates by leveraging In-Context Learning (ICL), which allows LLMs to learn new tasks from few-shot examples provided in the input. Using new-interest examples as the ICL few-shot examples, LLMs may learn real-time interest directly, avoiding the need for model updates. However, existing LLM-based recommenders often lose the in-context learning ability during recommendation tuning, while the original LLM's in-context learning lacks recommendation-specific focus. To address this, we propose RecICL, which customizes recommendation-specific in-context learning for real-time recommendations. RecICL organizes training examples in an in-context learning format, ensuring that in-context learning ability is preserved and aligned with the recommendation task during tuning. Extensive experiments demonstrate RecICL's effectiveness in delivering real-time recommendations without requiring model updates. Our code is available at https://github.com/ym689/rec_icl.