arxiv Preprint - LLM-Rec: Personalized Recommendation via Prompting Large Language Models

In this episode we discuss LLM-Rec: Personalized Recommendation via Prompting Large Language Models by Hanjia Lyu, Song Jiang, Hanqing Zeng, Qifan Wang, Si Zhang, Ren Chen, Chris Leung, Jiajie Tang, Yinglong Xia, Jiebo Luo. The paper examines different prompting strategies for improving personalized recommendation performance using large language models (LLMs) through input augmentation. The proposed approach, LLM-Rec, incorporates four prompting strategies, demonstrating that using LLM-generated augmented input text enhances recommendation performance. The recommendation-driven and engagement-guided prompting strategies highlight the LLM's comprehension of global and local item characteristics, underscoring the necessity of diverse prompts and input augmentation techniques to enhance recommendation capabilities with LLMs.