Inverse Constitutional AI

The alignment of large language models (LLMs) to human values becomes more and more pressing as their scale and capabilities have grown. One important feature of alignment is understanding the preference datasets that are used to finetune LLMs. Inverse Constitutional AI (ICAI) is presented as a nove...

Cijeli opis

Bibliografski detalji
Glavni autor: Kostolansky, Timothy H.
Daljnji autori: Hadfield-Menell, Dylan
Format: Disertacija
Izdano: Massachusetts Institute of Technology 2024
Online pristup:https://hdl.handle.net/1721.1/156804

Slični predmeti