用大模型投票生成真实用户行为，提升推荐系统准确性与公平性。
VoteGCL: Enhancing Graph-based Recommendations with Majority-Voting LLM-Rerank Augmentation
- 通过大模型多轮重排+多数投票，生成高置信度合成交互数据。
- 在多个数据集上准确率提升，且显著降低热门商品偏好偏差。
- 适合做推荐系统去偏、冷启动优化的研究者或工程师参考。
推荐系统常因用户-物品交互数据稀疏而表现下降，并加剧现实场景中的热门偏差。本文提出一种新型数据增强框架，利用大语言模型（LLMs）和物品文本描述来丰富交互数据。通过少样本提示多次调用大模型进行物品重排，并以多数投票聚合结果，生成高置信度的合成用户-物品交互数据，其有效性基于测度集中理论的理论保证。为有效利用增强数据，将该机制融入图对比学习框架，缓解分布偏移并减轻热门偏差。大量实验表明，该方法在多个基准上均优于强基线，提升推荐准确率并减少流行度偏差。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。