Balancing Fine-tuning and RAG: A Hybrid Strategy for Dynamic LLM Recommendation Updates

2025/10/23 by Meng, Changping, Ling, Hongyi, Wang, Jianling +9
#FOS: Computer and information sciences #Information Retrieval (cs.IR)

paper · doi:10.48550/arxiv.2510.20260

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.

Citations

• DLCRec: A Novel Approach for Managing Diversity in LLM-Based Recommender Systems
• LLMs for User Interest Exploration in Large-scale Recommendation Systems
• Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
• RIGHT: Retrieval-augmented Generation for Mainstream Hashtag Recommendation
• OpenP5: An Open-Source Platform for Developing, Training, and Evaluating LLM-based Recommender Systems
• Long-Term Value of Exploration: Measurements, Findings and Algorithms
• Show Me the Whole World: Towards Entire Item Space Exploration for Interactive Personalized Recommendations

Related

• User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systems
• LLMs for User Interest Exploration in Large-scale Recommendation Systems
• WebRec: Enhancing LLM-based Recommendations with Attention-guided RAG from Web
• Bridging the Gap: Self-Optimized Fine-Tuning for LLM-based Recommender Systems
• A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges