iknow-lab/JudgeBias-DPO-RefFree-testset download history

iknow-lab/JudgeBias-DPO-RefFree-testset is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 17 times (3 in the last 7 days), and 253 times in total. It ranks #417,311 among datasets by monthly downloads.

JudgeBias-DPO-RefFree-testset A fixed evaluation benchmark (1,000 samples) for assessing DPO-trained LLM judges on materials science synthesis recipe evaluation in a reference-free setting. Purpose This test set supports two evaluation methods: 1. Reward Accuracy (Log-P

Open iknow-lab/JudgeBias-DPO-RefFree-testset on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.