6 papers
On the Blessing of Pre-training in Weak-to-Strong Generalization
Wei Yao, Wang Zhaoyang, Gengze Xu +5
The paradigm of Weak-to-Strong Generalization (W2SG) suggests that a pre-trained strong model can surpass its weak supervisor, yet the decisive role of pre-training remains theoret…
Weak-to-Strong Generalization via Bregman Bias-Variance Decomposition
Gengze Xu, Wei Yao, Ziqiao Wang +1
Weak-to-strong generalization (W2SG) is the phenomenon in which a powerful student model, trained on labels produced by a weaker teacher, ultimately outperforms the teacher on the…
The Capabilities and Limitations of Weak-to-Strong Generalization: Generalization and Calibration
Wei Yao, Wenkai Yang, Gengze Xu +3
Weak-to-strong generalization, where weakly supervised strong models outperform their weaker teachers, offers a promising approach to aligning superhuman models with human values.…
On Weak-to-Strong Generalization and f-Divergence
Wei Yao, Gengze Xu, Huayi Tang +4
Weak-to-strong generalization (W2SG) has emerged as a promising paradigm for stimulating the capabilities of strong pre-trained models by leveraging supervision from weaker supervi…
Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL
Wei Yao, Wenkai Yang, Ziqiao Wang +2
As large language models advance toward superhuman performance, ensuring their alignment with human values and abilities grows increasingly complex. Weak-to-strong generalization o…
Understanding Model Ensemble in Transferable Adversarial Attack
Wei Yao, Zeliang Zhang, Huayi Tang +1
Model ensemble adversarial attack has become a powerful method for generating transferable adversarial examples that can target even unknown models, but its theoretical foundation…