1. It’s all in the name: Mitigating gender bias with name-based counterfactual data substitution;hall;In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP),2019
2. Neural Backdoors in NLP;guan,2019
3. Unbiased Classification through Bias-Contrastive and Bias-Balanced Learning;hong;In Proceedings of the 35th International Conference on Neural Information Processing Systems,2021
4. Mitigating the Position Bias of Transformer Models in Passage Re-ranking
5. Planting Undetectable Backdoors in Machine Learning Models;goldwasser;ArXiv abs/2204 06974,2022