EAGER: Entropy-Aware GEneRation for Adaptive Inference-Time Scaling Paper • 2510.11170 • Published 21 days ago • 1
BeaverTails Safety Classifiers Collection Safety classifiers fine-tuned on a bilingual dataset composed of the English QA pairs from BeaverTails and the Italian QA pairs from BeaverTails-IT. • 3 items • Updated Jul 23
Steering Large Language Models for Machine Translation Personalization Paper • 2505.16612 • Published May 22 • 6
Multi-property Steering of Large Language Models with Dynamic Activation Composition Paper • 2406.17563 • Published Jun 25, 2024 • 4