Recommendation systems often suffer from data sparsity caused by limited user-item interactions, which degrade their performance and amplify popularity bias in real-world scenarios. This paper proposes a novel data augmentation framework that leverages Large Language Models (LLMs) and item textual descriptions to enrich interaction data. By few-shot prompting LLMs multiple times to rerank items and aggregating the results via majority voting, we generate high-confidence synthetic user-item interactions, supported by theoretical guarantees based on the concentration of measure. To effectively leverage the augmented data in the context of a graph recommendation system, we integrate it into a graph contrastive learning framework to mitigate distributional shift and alleviate popularity bias. Extensive experiments show that our method improves accuracy and reduces popularity bias, outperforming strong baselines.
@article{arxiv.2507.21563,
title = {VoteGCL: Enhancing Graph-based Recommendations with Majority-Voting LLM-Rerank Augmentation},
author = {Minh-Anh Nguyen and Bao Nguyen and Ha Lan N. T. and Tuan Anh Hoang and Duc-Trong Le and Dung D. Le},
journal= {arXiv preprint arXiv:2507.21563},
year = {2026}
}