GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback

This paper proposes the "GNN-as-Judge" framework to enhance LLMs' performance in few-shot semi-supervised learning on Text-Attributed Graphs (TAGs) where labeled data is scarce. The method addresses the challenges of generating reliable pseudo-labels and mitigating label noise by incorporating the structural inductive bias of GNNs.