Gender bias in word embeddings: A comprehensive analysis of frequency, syntax, and semantics A Caliskan, PP Ajay, T Charlesworth, R Wolfe, MR Banaji Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, 156-170, 2022 | 41 | 2022 |
Low frequency names exhibit bias and overfitting in contextualizing language models R Wolfe, A Caliskan arXiv preprint arXiv:2110.00672, 2021 | 40 | 2021 |
American== white in multimodal language-and-image ai R Wolfe, A Caliskan Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, 800-812, 2022 | 32 | 2022 |
Markedness in visual semantic ai R Wolfe, A Caliskan Proceedings of the 2022 ACM Conference on Fairness, Accountability, and …, 2022 | 31 | 2022 |
Contrastive language-vision ai models pretrained on web-scraped multimodal data exhibit sexual objectification bias R Wolfe, Y Yang, B Howe, A Caliskan Proceedings of the 2023 ACM Conference on Fairness, Accountability, and …, 2023 | 24 | 2023 |
Evidence for hypodescent in visual semantic AI R Wolfe, MR Banaji, A Caliskan Proceedings of the 2022 ACM Conference on Fairness, Accountability, and …, 2022 | 23 | 2022 |
Evaluating biased attitude associations of language models in an intersectional context S Omrani Sabbaghi, R Wolfe, A Caliskan Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, 542-553, 2023 | 10 | 2023 |
Contrastive visual semantic pretraining magnifies the semantics of natural language representations R Wolfe, A Caliskan arXiv preprint arXiv:2203.07511, 2022 | 10 | 2022 |
Vast: The valence-assessing semantics test for contextualizing language models R Wolfe, A Caliskan Proceedings of the AAAI Conference on Artificial Intelligence 36 (10), 11477 …, 2022 | 8 | 2022 |
Detecting Emerging Associations and Behaviors With Regional and Diachronic Word Embeddings R Wolfe, A Caliskan 2022 IEEE 16th International Conference on Semantic Computing (ICSC), 91-98, 2022 | 2 | 2022 |