Leveraging Large Language Models (LLMs) to harness user-item interaction histories for item generation has emerged as a promising paradigm in generative recommendation. However, the limited context window of LLMs often restricts them to focusing on recent user interactions only, leading to the neglect of long-term interests involved in the longer histories. To address this challenge, we propose a novel Automatic Memory-Retrieval framework (AutoMR), which is capable of storing long-term interests in the memory and extracting relevant information from it for next-item generation within LLMs. Extensive experimental results on two real-world datasets demonstrate the effectiveness of our proposed AutoMR framework in utilizing long-term interests for generative recommendation.
@article{arxiv.2412.17593,
title = {Leveraging Memory Retrieval to Enhance LLM-based Generative Recommendation},
author = {Chengbing Wang and Yang Zhang and Fengbin Zhu and Jizhi Zhang and Tianhao Shi and Fuli Feng},
journal= {arXiv preprint arXiv:2412.17593},
year = {2025}
}