by Alon Benhaim Papers
2 papers found
Conference
POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization
Batuhan K. Karaman, ishmam zabir, Alon Benhaim et al.
ICML 2025posterarXiv:2410.12999
Scaling Optimal LR Across Token Horizons
Johan Bjorck, Alon Benhaim, Vishrav Chaudhary et al.
ICLR 2025posterarXiv:2409.19913
18
citations