Disentangled Graph-Enhanced Large Language Models for Fair Learning

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

IJCAI 20260 citations

Disentangled Graph-Enhanced Large Language Models for Fair Learning

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

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.

AI Ethics, Trust, Fairnes: Fairness and diversityAI Ethics, Trust, Fairnes: Trustworthy AINatural Language Processing: Language models

BibTeX

@inproceedings{ijcai2026_disentangledgrap,
  title = {Disentangled Graph-Enhanced Large Language Models for Fair Learning},
  author = {Zhipeng Yin and Zichong Wang and Zhong Chen and Jack Yang and Xin Ning and Wenbin Zhang},
  booktitle = {IJCAI 2026},
  year = {2026}
}