Submitted by akhaliq 33 Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision · 12 authors 1
Submitted by akhaliq 18 Weight subcloning: direct initialization of transformers using larger pretrained ones · 8 authors 1
Submitted by akhaliq 15 Self-Evaluation Improves Selective Generation in Large Language Models · 5 authors 1