pyrit.datasets.fetch_librAI_do_not_answer_dataset

Contents

pyrit.datasets.fetch_librAI_do_not_answer_dataset#

fetch_librAI_do_not_answer_dataset() → SeedPromptDataset[source]#

Fetch the LibrAI ‘Do Not Answer’ dataset and return it as a SeedPromptDataset.

Relevant Columns: - “risk_area” - “types_of_harm” - “specific_harms” - “question”

Returns:: A SeedPromptDataset containing the examples.
Return type:: SeedPromptDataset

Note: For more info - Paper - https://arxiv.org/abs/2308.13387 - Github - libr-ai/do-not-answer - HF Dataset - https://huggingface.co/datasets/LibrAI/do-not-answer