1 code implementation • 7 Jul 2023 • Shiva Omrani Sabbaghi, Robert Wolfe, Aylin Caliskan
Adapting the projection-based approach to embedding association tests that quantify bias, we find that language models exhibit the most biased attitudes against gender identity, social class, and sexual orientation signals in language.
1 code implementation • 21 Dec 2022 • Robert Wolfe, Yiwei Yang, Bill Howe, Aylin Caliskan
A first experiment uses standardized images of women from the Sexual OBjectification and EMotion Database, and finds that human characteristics are disassociated from images of objectified women: the model's recognition of emotional state is mediated by whether the subject is fully or partially clothed.
no code implementations • 1 Jul 2022 • Robert Wolfe, Aylin Caliskan
In an image captioning task, BLIP remarks upon the race of Asian individuals as much as 36% of the time, but never remarks upon race for White individuals.
no code implementations • 7 Jun 2022 • Aylin Caliskan, Pimparkar Parth Ajay, Tessa Charlesworth, Robert Wolfe, Mahzarin R. Banaji
Using the Single-Category Word Embedding Association Test, we demonstrate the widespread prevalence of gender biases that also show differences in: (1) frequencies of words associated with men versus women; (b) part-of-speech tags in gender-associated words; (c) semantic categories in gender-associated words; and (d) valence, arousal, and dominance in gender-associated words.
1 code implementation • 23 May 2022 • Robert Wolfe, Aylin Caliskan
The model is more likely to rank the unmarked "person" label higher than labels denoting gender for Male individuals (26. 7% of the time) vs.
1 code implementation • 22 May 2022 • Robert Wolfe, Mahzarin R. Banaji, Aylin Caliskan
We examine the state-of-the-art multimodal "visual semantic" model CLIP ("Contrastive Language Image Pretraining") for the rule of hypodescent, or one-drop rule, whereby multiracial people are more likely to be assigned a racial or ethnic label corresponding to a minority or disadvantaged racial or ethnic group than to the equivalent majority or advantaged group.
no code implementations • ACL 2022 • Robert Wolfe, Aylin Caliskan
We find that contrastive visual semantic pretraining significantly mitigates the anisotropy found in contextualized word embeddings from GPT-2, such that the intra-layer self-similarity (mean pairwise cosine similarity) of CLIP word embeddings is under . 25 in all layers, compared to greater than . 95 in the top layer of GPT-2.
1 code implementation • 14 Mar 2022 • Robert Wolfe, Aylin Caliskan
VAST, the Valence-Assessing Semantics Test, is a novel intrinsic evaluation task for contextualized word embeddings (CWEs).
no code implementations • EMNLP 2021 • Robert Wolfe, Aylin Caliskan
Moreover, we find Spearman's r between racial bias and name frequency in BERT of . 492, indicating that lower-frequency minority group names are more associated with unpleasantness.