| tags: | |
| - gender-bias | |
| - bert | |
| # Model Card for `mabel-bert-base-uncased` | |
| # Model Description | |
| This is the model for MABEL, as described in our paper, "[MABEL: Attenuating Gender Bias using Textual Entailment Data](https://arxiv.org/abs/2210.14975)". MABEL is trained from an underlying `bert-base-uncased` backbone, and demonstrates a good bias-performance tradeoff across a suite of intrinsic and extrinsic bias metrics. | |