Refusal-ablated DeepSeek-V4.1-Flash weights trend on Hugging Face
Publisher evals say full refusals fell from 81.62% to 4.30% while harmful-assistance labels rose to 78.28%, with MMLU nearly unchanged.
2
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #refusal-ablation
Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration
Researchers introduce Decoy Direction Optimization, a cheap weight-editing defense that blinds refusal-direction ablation attacks against open-weight LLM safety guardrails.