Hierarchical Dual Debiasing in LLM-based Recommendation

Abstract

Large language models (LLM) have emerged as a pivotal technique for enhancing the performance of modern recommender systems. Despite enjoying many advantages, LLM-based recommender systems (LRS) exhibit more severe popularity bias than conventional recommender systems (CRS). Compounding this issue, current debiasing methods for LRS are limited to single-level and single-stage interventions, resulting in suboptimal effectiveness. In this paper, we propose a novel LRS debiasing method that performs debiasing at both the token and item levels across the training and inference stages, so called Hierarchical Dual Debiasing in LRS (HD \({}^{2}\) LRS). Specifically, during the training stage, a token-wise inverse propensity score technique is embedded into the supervised fine-tuning phase, encouraging the LLM to focus more on unpopular tokens. Subsequently, a popularity-aware direct preference optimization method is developed to curb LLM's tendency to favor popular items. During the inference stage, we first train a highly biased CRS by amplifying the weights assigned to popular items. The prediction outputs of the biased CRS are then leveraged to constrain the LLM, preventing it from generating popular tokens and recommending popular items. Extensive experiments conducted on four real-world datasets confirm that our HD \({}^{2}\) LRS effectively alleviates popularity bias in LRS and yields significant improvements in recommendation accuracy.