Towards Conceptualization of “Fair Explanation”: Disparate Impacts of anti-Asian Hate Speech Explanations on Content Moderators

Tin Nguyen, Jiannan Xu, Aayushi Roy, Hal Daumé III, Marine Carpuat


Abstract
Recent research at the intersection of AI explainability and fairness has focused on how explanations can improve human-plus-AI task performance as assessed by fairness measures. We propose to characterize what constitutes an explanation that is itself “fair” – an explanation that does not adversely impact specific populations. We formulate a novel evaluation method of “fair explanations” using not just accuracy and label time, but also psychological impact of explanations on different user groups across many metrics (mental discomfort, stereotype activation, and perceived workload). We apply this method in the context of content moderation of potential hate speech, and its differential impact on Asian vs. non-Asian proxy moderators, across explanation approaches (saliency map and counterfactual explanation). We find that saliency maps generally perform better and show less evidence of disparate impact (group) and individual unfairness than counterfactual explanations. Content warning: This paper contains examples of hate speech and racially discriminatory language. The authors do not support such content. Please consider your risk of discomfort carefully before continuing reading!
Anthology ID:
2023.emnlp-main.602
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9696–9717
Language:
URL:
https://aclanthology.org/2023.emnlp-main.602
DOI:
10.18653/v1/2023.emnlp-main.602
Bibkey:
Cite (ACL):
Tin Nguyen, Jiannan Xu, Aayushi Roy, Hal Daumé III, and Marine Carpuat. 2023. Towards Conceptualization of “Fair Explanation”: Disparate Impacts of anti-Asian Hate Speech Explanations on Content Moderators. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9696–9717, Singapore. Association for Computational Linguistics.
Cite (Informal):
Towards Conceptualization of “Fair Explanation”: Disparate Impacts of anti-Asian Hate Speech Explanations on Content Moderators (Nguyen et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.602.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.602.mp4