← Search

Youtao Ding

1 accepted papers

2026

SceneJailEval: A Scenario-Adaptive Multi-Dimensional Framework for Jailbreak Evaluation

AAAI 2026technical

Accurate jailbreak evaluation is critical for LLM red team testing and jailbreak research. Mainstream methods rely on binary classification (string matching, toxic text classifiers, and LLM-based methods), outputting only "yes/no" labels without quantifying harm severity. Emerged multi-dimensional f

Cited by 0SourcePDFScholar