Search results for: RLHF - Bridge of Knowledge

Search results for: RLHF

results on page:
embed this view on your website

Displayed results came from alternative search method.

Filters

total: 1

clear all filters disabled

WikiPrefs: human preferences dataset build from text edits
Open Research Data
open access
- J. Majkutewicz
- J. Szymański
The WikiPrefs dataset is a human preferences dataset for Large Language Models alignment. It was built using the EditPrefs method from historical edits of Wikipedia featured articles