English

FairFlow: Mitigating Dataset Biases through Undecided Learning

Machine Learning 2025-03-25 v1 Artificial Intelligence Computation and Language

Abstract

Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing framework called ``FairFlow'' that mitigates dataset biases by learning to be undecided in its predictions for data samples or representations associated with known or unknown biases. The framework introduces two key components: a suite of data and model perturbation operations that generate different biased views of input samples, and a contrastive objective that learns debiased and robust representations from the resulting biased views of samples. Experiments show that FairFlow outperforms existing debiasing methods, particularly against out-of-domain and hard test samples without compromising the in-domain performance

Keywords

Cite

@article{arxiv.2503.17632,
  title  = {FairFlow: Mitigating Dataset Biases through Undecided Learning},
  author = {Jiali Cheng and Hadi Amiri},
  journal= {arXiv preprint arXiv:2503.17632},
  year   = {2025}
}

Comments

EMNLP 2024

R2 v1 2026-06-28T22:30:39.563Z