@inproceedings{zhiqiang-etal-2025-judge,
    title = "Judge and Improve: Towards a Better Reasoning of Knowledge Graphs with Large Language Models",
    author = "Zhiqiang, Mo  and
      Hua, Yang  and
      Li, Jiahui  and
      Liu, Yuan  and
      Wong, Shawn  and
      Huang, Jianmin",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.269/",
    pages = "5303--5320",
    ISBN = "979-8-89176-332-6",
    abstract = "Graph Neural Networks (GNNs) have shown immense potential in improving the performance of large-scale models by effectively incorporating structured relational information. However, current approaches face two key challenges: (1) achieving robust semantic alignment between graph representations and large models, and (2) ensuring interpretability in the generated outputs. To address these challenges, we propose ExGLM (Explainable Graph Language Model), a novel training framework designed to seamlessly integrate graph and language modalities while enhancing transparency. Our framework introduces two core components: (1) a graph-language synergistic alignment module, which aligns graph structures with language model to ensure semantic consistency across modalities; and (2) a judge-and-improve paradigm, which allows the language model to iteratively evaluate, refine, and prioritize responses with higher interpretability, thereby improving both performance and transparency. Extensive experiments conducted on three benchmark datasets{---}ogbn-arxiv, Cora, and PubMed{---}demonstrate that ExGLM not only surpasses existing methods in efficiency but also generates outputs that are significantly more interpretable, effectively addressing the primary limitations of current approaches."
}