MABEL: Attenuating Gender Bias using Textual Entailment Data

Jacqueline He, Mengzhou Xia, Christiane Fellbaum, Danqi Chen

Research output: Contribution to conferencePaperpeer-review

4 Scopus citations


Pre-trained language models encode undesirable social biases, which are further exacerbated in downstream use. To this end, we propose MABEL (a Method for Attenuating Gender Bias using Entailment Labels), an intermediate pre-training approach for mitigating gender bias in contextualized representations. Key to our approach is the use of a contrastive learning objective on counterfactually augmented, gender-balanced entailment pairs from natural language inference (NLI) datasets. We also introduce an alignment regularizer that pulls identical entailment pairs along opposite gender directions closer. We extensively evaluate our approach on intrinsic and extrinsic metrics, and show that MABEL outperforms previous task-agnostic debiasing approaches in terms of fairness. It also preserves task performance after fine-tuning on downstream tasks. Together, these findings demonstrate the suitability of NLI data as an effective means of bias mitigation, as opposed to only using unlabeled sentences in the literature. Finally, we identify that existing approaches often use evaluation settings that are insufficient or inconsistent. We make an effort to reproduce and compare previous methods, and call for unifying the evaluation settings across gender debiasing methods for better future comparison.

Original languageEnglish (US)
Number of pages22
StatePublished - 2022
Event2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022 - Abu Dhabi, United Arab Emirates
Duration: Dec 7 2022Dec 11 2022


Conference2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems


Dive into the research topics of 'MABEL: Attenuating Gender Bias using Textual Entailment Data'. Together they form a unique fingerprint.

Cite this