Ahmad Beirami

7

Papers

401

Total Citations

Papers (7)

Safety Alignment Should be Made More Than Just a Few Tokens Deep

Theoretical guarantees on the best-of-n alignment policy

Block Verification Accelerates Speculative Decoding

Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

FRAPPÉ: A Group Fairness Framework for Post-Processing Everything

Controlled Decoding from Language Models