Measuring Fairness with Biased Rulers: A Comparative Study on Bias Metrics for Pre-trained Language Models

Pieter Delobelle, Ewoenam Tokpo, Toon Calders, Bettina Berendt


Abstract
An increasing awareness of biased patterns in natural language processing resources such as BERT has motivated many metrics to quantify ‘bias’ and ‘fairness’ in these resources. However, comparing the results of different metrics and the works that evaluate with such metrics remains difficult, if not outright impossible. We survey the literature on fairness metrics for pre-trained language models and experimentally evaluate compatibility, including both biases in language models and in their downstream tasks. We do this by combining traditional literature survey, correlation analysis and empirical evaluations. We find that many metrics are not compatible with each other and highly depend on (i) templates, (ii) attribute and target seeds and (iii) the choice of embeddings. We also see no tangible evidence of intrinsic bias relating to extrinsic bias. These results indicate that fairness or bias evaluation remains challenging for contextualized language models, among other reasons because these choices remain subjective. To improve future comparisons and fairness evaluations, we recommend to avoid embedding-based metrics and focus on fairness evaluations in downstream tasks.
Anthology ID:
2022.naacl-main.122
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1693–1706
Language:
URL:
https://aclanthology.org/2022.naacl-main.122
DOI:
10.18653/v1/2022.naacl-main.122
Bibkey:
Cite (ACL):
Pieter Delobelle, Ewoenam Tokpo, Toon Calders, and Bettina Berendt. 2022. Measuring Fairness with Biased Rulers: A Comparative Study on Bias Metrics for Pre-trained Language Models. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1693–1706, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Measuring Fairness with Biased Rulers: A Comparative Study on Bias Metrics for Pre-trained Language Models (Delobelle et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.122.pdf
Software:
 2022.naacl-main.122.software.zip
Video:
 https://aclanthology.org/2022.naacl-main.122.mp4
Data
CrowS-PairsStereoSetWinoBias