GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods
GuidedBench, a novel benchmark comprising a curated harmful question dataset and GuidedEval, an evaluation system integrated with detailed case-by-case evaluation guidelines are introduced, ensuring reliable and reproducible evaluations.
Ruixuan Huang, Xun-Guang Wang, Zongjie Li et al.
· 8 citations