[3F4-OS-42a] OS-42

[3F4-OS-42a-05] Analyzing Popularity Bias in Generative Recommendations From the View of Memorization

〇Shotaro Ishihara¹ (1. Nikkei Inc.)

Keywords:Generative Recommendations, Memorization, Popularity Bias, Large Language Models, News

While there is a growing interest in applying large language models to recommendations, the discussion of fairness is still in its infancy. This study focuses on the memorization of training data, which is pointed out as one of the issues of large language models, for analyzing generative recommendations. Specifically, we finetuned Llama3 on log data from the Japanese news media to predict the transition of viewed articles and quantified the memorization of training data. The results suggested that there is a bias that excessively recommends popular articles, and this can be interpreted from the view of memorizing training data. We also demonstrated that deduplication, a technique for mitigating memorization bias, can be used to reduce the popularity bias in generative recommendations.