harmful-datasets-llm-labeled - a deepkeep-ai Collection

deepkeep-ai 's Collections

harmful-datasets-llm-labeled

Jailbreak Attacks Datasets

Internal Benchmarking Datasets

production-models

harmful-datasets-llm-labeled

updated 9 days ago

Harmful/safe datasets with LLM-derived binary labels (any multihead subtype True → harmful)

This collection has no items.