# VoteGCL: Enhancing Graph-based Recommendations with Majority-Voting LLM-Rerank Augmentation

arXiv: https://arxiv.org/abs/2507.21563 · HTML: https://mlsanity.com/paper/2507.21563/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 29 Jul 2025.

## Builds on (most cited first, 26 of 26)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Large Language Models are Zero-Shot Rankers for Recommender Systems](https://mlsanity.com/paper/2305.08845/) (2023)
- [Self-supervised Graph Learning for Recommendation](https://mlsanity.com/paper/2010.10783/) (2020)
- [Contrastive Learning Inverts the Data Generating Process](https://mlsanity.com/paper/2102.08850/) (2021)
- [Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2112.08679/) (2021)
- [LLMRec: Large Language Models with Graph Augmentation for Recommendation](https://mlsanity.com/paper/2311.00423/) (2023)
- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [Data Augmentation for Deep Graph Learning: A Survey](https://mlsanity.com/paper/2202.08235/) (2022)
- [Managing Popularity Bias in Recommender Systems with Personalized Re-ranking](https://mlsanity.com/paper/1901.07555/) (2019)
- [Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models](https://mlsanity.com/paper/2306.10933/) (2023)
- [XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2209.02544/) (2022)
- [ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models](https://mlsanity.com/paper/2305.06566/) (2023)
- [CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation](https://mlsanity.com/paper/2403.06447/) (2024)
- [Graph Transformer for Recommendation](https://mlsanity.com/paper/2306.02330/) (2023)
- [Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregation](https://mlsanity.com/paper/2401.13870/) (2024)
- [Contrastive Cross-domain Recommendation in Matching](https://mlsanity.com/paper/2112.00999/) (2021)
- [Graph Collaborative Signals Denoising and Augmentation for Recommendation](https://mlsanity.com/paper/2304.03344/) (2023)
- [SelfCF: A Simple Framework for Self-supervised Collaborative Filtering](https://mlsanity.com/paper/2107.03019/) (2021)
- [Graph Augmentation for Recommendation](https://mlsanity.com/paper/2403.16656/) (2024)
- [Large Language Model Enhanced Hard Sample Identification for Denoising Recommendation](https://mlsanity.com/paper/2409.10343/) (2024)

## Abstract (arXiv)

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.