The fetch_adv_bench_dataset currently does not have any applied harm categories to the different prompts. We want to be able to use this dataset with harm category filters and this requires we manually apply category labels to the dataset to use in PyRIT.
This may look like adding harm categories in a separate file to import into PyRIT instead of using this CSV file in the fetch function here: https://github.com/Azure/PyRIT/blob/main/pyrit/datasets/fetch_example_datasets.py
The
fetch_adv_bench_datasetcurrently does not have any applied harm categories to the different prompts. We want to be able to use this dataset with harm category filters and this requires we manually apply category labels to the dataset to use in PyRIT.This may look like adding harm categories in a separate file to import into PyRIT instead of using this CSV file in the fetch function here: https://github.com/Azure/PyRIT/blob/main/pyrit/datasets/fetch_example_datasets.py