Optimizing Novelty of Top-k Recommendations using Large Language Models and Reinforcement Learning

arXiv:2406.14169v1 Announce Type: cross
Abstract: Given an input query, a recommendation model is trained using user feedback data (e.g., click data) to output a ranked list of items. In real-world systems, besides accuracy, an important consideration for a new model is novelty of its top-k recommendations w.r.t. an existing deployed model. However, novelty of top-k items is a difficult goal to optimize a model for, since it involves a non-differentiable sorting operation on the model's predictions. Moreover, novel items, by …

abstract accuracy arxiv click cs.ir cs.lg data feedback important input language language models large language large language models list output query recommendation recommendation model recommendations reinforcement reinforcement learning systems type user feedback world