Language Models - Groups

SafeDecoding dataset

The dataset used in the SafeDecoding paper, which contains 32 harmful queries spanning 16 harmful categories.
- Dataset
- JSON
Comprehensive Assessment of Jailbreak Attacks against LLMs

The Comprehensive Assessment of Jailbreak Attacks against LLMs dataset is used to evaluate the effectiveness of jailbreak attacks on language models.
- Dataset
- JSON

Before browse our site, please accept our cookies policy

2 datasets found