Wildjailbreak

WildJailbreak Dataset Card WildJailbreak is an open-source synthetic safety-training dataset with 262K vanilla (direct harmful requests) and adversarial (complex adversarial jailbreaks) prompt-response pairs. In order to mitigate exaggerated safety behaviors, WildJailbreaks provides two contrastive types of queries: 1)

Papers using Wildjailbreak (2)

ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs2026Learning to Extract Context for Context-Aware LLM Inference2025