AIBullisharXiv – CS AI · 7h ago7/10
🧠
ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing
Researchers introduce ALIGNBEAM, a training-free inference-time defense that transfers safety alignment between different language model families by translating logits across vocabularies. The method addresses a critical gap where existing safety defenses fail for cross-family model pairs, enabling safety constraints without modifying model weights or retraining.