NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#llm-refusal

1 stories this week · 2 this month · 2 in 6 months · mostly AI

Stories per day · 30 days

Relatedabliteration1 activation-steering1 alignment1 gemini1 harmbench1 mistral1 model-evaluation1 multilingual1

2 stories, newest first · one card per story

arXiv cs.CR2d ago

Component translation does not reliably change LLM refusal rates

On 190 harmful behaviours, only an exploratory Mistral Small 4 Spanish swap stayed significant after correction.

llm-refusal multilingual

1

arXiv cs.AI / cs.LG / cs.CL9d ago

WRDO learns weighted directions to change LLM refusal behavior

The method is tested on three open-weight models with HarmBench and can also be reversed to restore refusal.

llm-refusal alignment

2