Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
Weak-model supervision experiments presented as an analogy for supervising superhuman models.
- Issued by
- Authors credited
- No authorship claim recorded yet. The source record lists Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, Ilya Sutskever and Jeff Wu.
- Dates
- Published 2023-12-14
- Exact source
- Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision arXiv · published 2023-12-14 · arXiv:2312.09390v1; first-submission date from version history. Later revisions are not substituted.
Appears in
No collection holds a record about this document yet.
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Issue and authorship records
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Cites · 4
Explicit references in this document. Citation is neither agreement nor influence.
Discusses · 1
Concepts explicitly discussed. No earliest use, invention or transmission is claimed.
Not recorded for this document: cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · reports evaluation of. A missing record does not show that the relation does not exist.