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...
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
-
Image inversion and uncertainty quantification for constitutive laws of pattern formation
od: Zhao, Hongbo, i dr.
Izdano: (2022) -
Image inversion and uncertainty quantification for constitutive laws of pattern formation
od: Zhao, Hongbo, i dr.
Izdano: (2021) -
A model for an inverse power constitutive law for cerebral compliance
od: Wirth, B, i dr.
Izdano: (2008) -
AI-assisted reaction impurity prediction and inverse structure elucidation
od: Mohapatra, Somesh
Izdano: (2024) -
Constitution and constitutionalism
od: Moten, Abdul Rashid
Izdano: (2008)