Trustworthiness properties such as fairness and robustness can be transferred to stronger language models when both the weak teacher and strong student are explicitly regularized, but privacy does not transfer.
Weak-to-strong generalization: Eliciting strong capabilities with weak supervision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
Trustworthiness properties such as fairness and robustness can be transferred to stronger language models when both the weak teacher and strong student are explicitly regularized, but privacy does not transfer.