ML Anthology
Authors
Search
About
Elgohary, Ahmed
2 publications
ICLR
2025
Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
Jingyu Zhang
,
Ahmed Elgohary
,
Ahmed Magooda
,
Daniel Khashabi
,
Benjamin Van Durme
NeurIPSW
2024
Controllable Safety Alignment: Adapting LLMs to Diverse Safety Requirements Without Re-Training
Jingyu Zhang
,
Ahmed Elgohary
,
Ahmed Magooda
,
Daniel Khashabi
,
Benjamin Van Durme