Papers by Sarah Alnegheimish
Using Natural Sentence Prompts for Understanding Biases in Language Models (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent work has shown that language models are susceptible to biases present in the training dataset. |
| Approach: | They propose to use natural sentence prompts to analyze gender-occupation biases in language models. |
| Outcome: | The proposed dataset can be used to analyze gender-occupation biases in language models. |