© 2026 Buobe

When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment | Healthy ML

Published by

on •1 min read

When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment | Healthy ML

Yuxin Xiao is a Ph.D. candidate at MIT IDSS.

When Style Breaks Safety Defending

When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment | Healthy ML | Buobe