3 papers
cs.LG2026
LLMs Can Annotate Attribution Graphs
Ameen Patel, Max Zhang, Nathan Hu
Circuit tracing is an exciting technique for revealing the internal computation of language models, but it requires a time-intensive manual step of grouping individual features or…
cs.CL2026
Why Do Safety Guardrails Degrade Across Languages?
Max Zhang, Ameen Patel, Sang T. Truong +1
Large language models exhibit safety degradation in non-English languages. Standard evaluation relies on Jailbreak Success Rate (JSR), which confounds several safety-driving factor…
cs.CL2025
Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety
Max Zhang, Derek Liu, Kai Zhang +2
Large language models (LLMs) are increasingly deployed worldwide, yet their safety alignment remains predominantly English-centric. This allows for vulnerabilities in non-English c…