Scientific Judge

paper dataset
Baidu
Introduced Reinforcement Learning from Community Feedback (RLCF) for aligning AI with scientific reasoning, accompanied by a dataset of 700,000 scientific preference signals.
Paper (arXiv)GitHubProject Page

Outputs 2

Scientific Judge

paper

Introduced Reinforcement Learning from Community Feedback (RLCF) for aligning AI with scientific reasoning.

Paper (arXiv)GitHubProject Page

Scientific Judge Dataset

dataset

Dataset of 700,000 scientific preference signals for alignment research.

Paper (arXiv)GitHub
trainingreasoningresearch