works on
autoregressive conditioning 1causal probing 1jailbreak attacks 1language model safety 1response-site mechanisms 1

From the 1 of 7 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language Models

Dasol Choi, Alex Kwon

Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action i…