Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
Uni-RLHFuni-rlhf.github.ioUni RLHF is a universal platform and benchmark suite for reinforcement learning with diverse human feedback, providing a complete workflow from real human annotation to offline RLHF baselines. It includes a multi-feedback annotation platform, large-scale crowdsourced datasets with over 15 million steps across 32 tasks, and modular baseline implementations to standardize RLHF research.
Parse Score
Sources
arxiv.org shapes more of what AI says about Uni-RLHF than any other source, at 100% of its citations.
