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...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2024
|
| Online Access: | https://hdl.handle.net/1721.1/156804 |