3 results found Sort:

EMNLP 2020: "Dialogue Response Ranking Training with Large-Scale Human Feedback Data"
Created 2020-09-03
108 commits to master branch, last one about a year ago
BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
Created 2023-06-14
3 commits to main branch, last one 11 months ago
The Prism Alignment Project
Created 2024-03-06
12 commits to main branch, last one 2 months ago