ALIGNBEAM: Transferring Safety Alignment Across Model Families at Inference Time
Domain fine-tuning erodes safety alignment — and existing logit-mixing defenses don't work when the draft and safety models use different vocabularies. ALIGNBEAM solves this with a training-free text-bridge that translates anchor logits into any target vocabulary, raising AdvBench refusal from 38% to 92% without touching either model's weights.