- Given the increasing role of artificial intelligence (AI) in many decision-making processes, we investigate the presence of AI bias towards terms related to a range of neurodivergent conditions, including autism, ADHD, schizophrenia, and obsessive-compulsive disorder (OCD). We use eleven different language model encoders to test the degree to which words related to neurodiversity are associated with groups of words related to danger, disease, badness, and other negative concepts. For each group of words tested, we report the mean strength of association (Word Embedding Association Test (WEAT) score) averaged over all encoders and find generally high levels of bias. Additionally, we show that bias occurs even when ... [Read More]
- Total Size
- 7 files (1.98 MB)
- Data Citation
- Brandsen, S., Chandrasekhar, T., Franz, L., Grapel, J., Dawson, G., & Carlson, D. (2024). Scripts from: Prevalence of Bias against Neurodivergence-Related Terms in Artificial Intelligence Language Models. Duke Research Data Repository. https://doi.org/10.7924/r4xw4mn8r
- DOI
- 10.7924/r4xw4mn8r
- Publication Date
- February 5, 2024
- ARK
- ark:/87924/r4xw4mn8r
- Affiliation
- Publisher
- Collection Dates
- January 1, 2023 - January 24, 2024
- Type
- Related Materials
- Contact
- Sam Brandsen,sam.brandsen@duke.edu, 984-209-0419, https://orcid.org/0009-0000-5687-2412
- Title
- Scripts from: Prevalence of Bias against Neurodivergence-Related Terms in Artificial Intelligence Language Models
- Repository
| Thumbnail | Title | Date Uploaded | Visibility | Actions |
|---|---|---|---|---|
|
|
README.pdf | 2024-02-05 | Download | |
|
File1.ipynb | 2024-02-05 | Download | |
|
|
File2.ipynb | 2024-02-05 | Download | |
|
|
File3.ipynb | 2024-02-05 | Download | |
|
|
File4.ipynb | 2024-02-05 | Download | |
|
|
Individual_Terms.ipynb | 2024-02-05 | Download | |
|
|
Significance_Tests.ipynb | 2024-02-05 | Download |
README or associated documentation cannot be displayed. Please reference the file list.