ibm-research/AttaQ download history
ibm-research/AttaQ is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 614 times (313 in the last 7 days), and 34,854 times in total. It ranks #28,072 among datasets by monthly downloads.
AttaQ Dataset Card The AttaQ red teaming dataset, consisting of 1402 carefully crafted adversarial questions, is designed to evaluate Large Language Models (LLMs) by assessing their tendency to generate harmful or undesirable responses. It may serve as a benchmark to assess the potential