Ahmed Elgohary

Introducing 𝐉𝐚𝐢𝐥𝐛𝐫𝐞𝐚𝐤 𝐃𝐢𝐬𝐭𝐢𝐥𝐥𝐚𝐭𝐢𝐨𝐧 🧨 (EMNLP '25 Findings) We propose a generate-then-select pipeline to "distill" effective jailbreak attacks into safety benchmarks, ensuring eval results are reproducible and robust to benchmark saturation & contamination🧵

🤖 LLMs are powerful, but their "one-size-fits-all" safety alignment limits flexibility. Safety standards vary across cultures and users—what’s safe in one context might not be in another. 🌍 We propose ✨Controllable Safety Alignment✨ for inference-time safety adaptation! 🧵👇

🤖 LLMs are powerful, but their "one-size-fits-all" safety alignment limits flexibility. Safety standards vary across cultures and users—what’s safe in one context might not be in another. 🌍 We propose ✨Controllable Safety Alignment✨ for inference-time safety adaptation! 🧵👇