/model_size_and_gender_bias

Code for "Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias" by Yarden Tal, Inbal Magar and Roy Schwartz, 4rd Workshop on Gender Bias in Natural Language, NAACL 2022.

Primary LanguagePython

Model-Size-and-Gender-Bias

Code for "Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias" by Yarden Tal, Inbal Magar and Roy Schwartz, 4rd Workshop on Gender Bias in Natural Language, NAACL 2022.

Setup

The code is implemented in python 3.7.3 using Hugging Face's transformers. To run it, please install the requirements.txt file:

pip install -r requirements.txt

Cite

@inproceedings{Tal:2022,
    author = {Yarden Tal and Inbal Magar and Roy Schwartz},
    title = {Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias},
    booktitle = {In Proc. of GeBNLP},
    month = July,
    year = {2022},
    doi = {10.48550/ARXIV.2206.09860},
    url = {https://arxiv.org/abs/2206.09860}
}

Contact

For inquiries, please send an email to yarden.tal1@mail.huji.ac.il.