most citedConstitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

7 citations · 10 across the 3 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2026

Segment-Level Coherence for Robust Harmful Intent Probing in LLMs

Xuanli He, Bilgehan Sel, Faizan Ali +3

Large Language Models (LLMs) are increasingly exposed to adaptive jailbreaking, particularly in high-stakes Chemical, Biological, Radiological, and Nuclear (CBRN) domains. Although…

cs.CL2025★ 7 cited

Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

Mrinank Sharma, Meg Tong, Jesse Mu +40

Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes…