Proceedings

Disentangled Graph-Enhanced Large Language Models for Fair Learning

Zhipeng Yin, Zichong Wang, Zhong Chen, Jack Yang, Xin Ning, Wenbin Zhang

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 844-852.

https://doi.org/10.24963/ijcai.2026/95

Keywords

  • AI Ethics, Trust, Fairnes: Fairness and diversity
  • Natural Language Processing: Language models
  • AI Ethics, Trust, Fairnes: Trustworthy AI

Abstract

Large Language Models (LLMs) achieve strong performance in many applications but remain limited in handling graph-structured data due to their reliance on textual context. Recent approaches integrate Graph Neural Networks (GNNs) to enhance structural modeling, yet they largely overlook fairness, leaving models vulnerable to bias amplification across graph and text modalities. To address this issue, we propose FairGEnt, a disentangled graph-enhanced large language model for fair graph learning. FairGEnt separates sensitive-related and sensitive-invariant factors in both graph and textual representations to mitigate bias while preserving task-relevant information, and further aligns the two modalities through a fairness-aware integration module. In addition, FairGEnt incorporates fair graph-enhanced instruction tuning to improve LLM understanding of complex graph structures. Experiments on multiple benchmark datasets demonstrate that FairGEnt consistently outperforms existing methods in both fairness and predictive performance.

Zhipeng Yin, Zichong Wang, Zhong Chen, Jack Yang, Xin Ning, and Wenbin Zhang. 2026. Disentangled Graph-Enhanced Large Language Models for Fair Learning. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 844–852. https://doi.org/10.24963/ijcai.2026/95
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards