-
Notifications
You must be signed in to change notification settings - Fork 591
FEAT adding transphobia awareness dataset #989
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice work! Just a few small things for cleanup. Glad to have this dataset added!
|
@romanlutz Sorry, I thought I was resolving conflicts and merging it to my forked repo, didn't realize I was attempting to merge to the azure pyrit's main branch |
|
|
@microsoft-github-policy-service agree |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks great! Just a few more small things
Add Transphobia Awareness Dataset Integration and Unit Test to PyRIT
Summary
This introduces the integration of the Transphobia Awareness Dataset into PyRIT, enabling users to fetch, analyze, and utilize this dataset for LLM safety and inclusivity evaluation. It also includes a unit test to check if the dataset loader works as expected.
Key Changes
1. New Dataset Loader
pyrit/datasets/transphobia_awareness_dataset.pyfetch_transphobia_awareness_dataset.SeedPromptwith appropriate metadata and harm categories.SeedPromptDatasetwith all prompts and dataset-level metadata."transphobia".2. Unit Test
tests/unit/datasets/test_transphobia_awareness_dataset.pySeedPromptDatasetwith valid prompts and correct harm categories.SeedPromptmatches the mock data, ensuring the loader logic is valid and not dependent on external data sources.How to Test
Run the unit test:
Try the example script (if present):
Why is this Important?
Checklist
References
@romanlutz Requesting review.