Abstract
Transformer-based pre-trained models are known to encode societal biases not only in their contextual representations, but also in downstream predictions when fine-tuned on task-specific data.We present D-Bias, an approach that selectively eliminates stereotypical associations (e.g, co-occurrence statistics) at fine-tuning, such that the model doesn’t learn to excessively rely on those signals.D-Bias attenuates biases from both identity words and frequently co-occurring proxies, which we select using pointwise mutual information.We apply D-Bias to a) occupation classification, and b) toxicity classification and find that our approach substantially reduces downstream biases (e.g. by > 60% in toxicity classification, for identities that are most frequently flagged as toxic on online platforms).In addition, we show that D-Bias dramatically improves upon scrubbing, i.e., removing only the identity words in question.We also demonstrate that D-Bias easily extends to multiple identities, and achieves competitive performance with two recently proposed debiasing approaches: R-LACE and INLP.- Anthology ID:
- 2022.findings-emnlp.372
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2022
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5073–5085
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.372
- DOI:
- 10.18653/v1/2022.findings-emnlp.372
- Cite (ACL):
- Swetasudha Panda, Ari Kobren, Michael Wick, and Qinlan Shen. 2022. Don’t Just Clean It, Proxy Clean It: Mitigating Bias by Proxy in Pre-Trained Models. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5073–5085, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Don’t Just Clean It, Proxy Clean It: Mitigating Bias by Proxy in Pre-Trained Models (Panda et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2022.findings-emnlp.372.pdf