Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts

arXiv:2402.15505v1 Announce Type: new
Abstract: Steering the behavior of a strong model pre-trained on internet-scale data can be difficult due to the scarcity of competent supervisors. Recent studies reveal that, despite supervisory noises, a strong student model may surpass its weak teacher when fine-tuned on specific objectives. Yet, the effectiveness of such weak-to-strong generalization remains limited, especially in the presence of large capability gaps. In this paper, we propose to address this challenge by harnessing a diverse set of specialized …

arxiv cs.ai cs.cv cs.lg experts hierarchical mixture of experts supervised learning type