{"ID":2851013,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.20260","arxiv_id":"2510.20260","title":"Balancing Fine-tuning and RAG: A Hybrid Strategy for Dynamic LLM Recommendation Updates","abstract":"Large Language Models (LLMs) empower recommendation systems through their advanced reasoning and planning capabilities. However, the dynamic nature of user interests and content poses a significant challenge: While initial fine-tuning aligns LLMs with domain knowledge and user preferences, it fails to capture such real-time changes, necessitating robust update mechanisms. This paper investigates strategies for updating LLM-powered recommenders, focusing on the trade-offs between ongoing fine-tuning and Retrieval-Augmented Generation (RAG). Using an LLM-powered user interest exploration system as a case study, we perform a comparative analysis of these methods across dimensions like cost, agility, and knowledge incorporation. We propose a hybrid update strategy that leverages the long-term knowledge adaptation of periodic fine-tuning with the agility of low-cost RAG. We demonstrate through live A/B experiments on a billion-user platform that this hybrid approach yields statistically significant improvements in user satisfaction, offering a practical and cost-effective framework for maintaining high-quality LLM-powered recommender systems.","short_abstract":"Large Language Models (LLMs) empower recommendation systems through their advanced reasoning and planning capabilities. However, the dynamic nature of user interests and content poses a significant challenge: While initial fine-tuning aligns LLMs with domain knowledge and user preferences, it fails to capture such real...","url_abs":"https://arxiv.org/abs/2510.20260","url_pdf":"https://arxiv.org/pdf/2510.20260v1","authors":"[\"Changping Meng\",\"Hongyi Ling\",\"Jianling Wang\",\"Yifan Liu\",\"Shuzhou Zhang\",\"Dapeng Hong\",\"Mingyan Gao\",\"Onkar Dalal\",\"Ed Chi\",\"Lichan Hong\",\"Haokai Lu\",\"Ningren Han\"]","published":"2025-10-23T06:31:00Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}