Red Teaming Innodata Jailbreaking
Introduced in Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations2024
The Innodata Red Teaming Prompts aims to rigorously assess models’ factuality and safety. This dataset, due to its manual creation and breadth of coverage, facilitates a comprehensive examination of LLM performance across diverse scenarios.