CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation

no code implementations • 11 Mar 2024 • Junda Wu, Cheng-Chun Chang, Tong Yu, Zhankui He, Jianing Wang, Yupeng Hou, Julian McAuley

Based on the retrieved user-item interactions, the LLM can analyze shared and distinct preferences among users, and summarize the patterns indicating which types of users would be attracted by certain items.

Recommendation Systems Reinforcement Learning (RL) +1