McGill-NLP/AdvBench-IR download history
McGill-NLP/AdvBench-IR is a question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 45 times (6 in the last 7 days), and 1,329 times in total. It ranks #200,643 among datasets by monthly downloads.
Exploiting Instruction-Following Retrievers for Malicious Information Retrieval This dataset includes malicious documents in response to AdvBench (Zou et al., 2023) queries. We have generated these documents using the Mistral-7B-Instruct-v0.2 language model. from datasets import load_datase