English

Debiasing Neural Retrieval via In-batch Balancing Regularization

Information Retrieval 2022-05-20 v1 Artificial Intelligence Computers and Society

Abstract

People frequently interact with information retrieval (IR) systems, however, IR models exhibit biases and discrimination towards various demographics. The in-processing fair ranking methods provide a trade-offs between accuracy and fairness through adding a fairness-related regularization term in the loss function. However, there haven't been intuitive objective functions that depend on the click probability and user engagement to directly optimize towards this. In this work, we propose the In-Batch Balancing Regularization (IBBR) to mitigate the ranking disparity among subgroups. In particular, we develop a differentiable \textit{normed Pairwise Ranking Fairness} (nPRF) and leverage the T-statistics on top of nPRF over subgroups as a regularization to improve fairness. Empirical results with the BERT-based neural rankers on the MS MARCO Passage Retrieval dataset with the human-annotated non-gendered queries benchmark \citep{rekabsaz2020neural} show that our IBBR method with nPRF achieves significantly less bias with minimal degradation in ranking performance compared with the baseline.

Keywords

Cite

@article{arxiv.2205.09240,
  title  = {Debiasing Neural Retrieval via In-batch Balancing Regularization},
  author = {Yuantong Li and Xiaokai Wei and Zijian Wang and Shen Wang and Parminder Bhatia and Xiaofei Ma and Andrew Arnold},
  journal= {arXiv preprint arXiv:2205.09240},
  year   = {2022}
}

Comments

9 pages, 1 figure, and 3 tables. A version appears in the Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP), 2022

R2 v1 2026-06-24T11:21:41.981Z