mair-lab/lave-human-feedback download history
mair-lab/lave-human-feedback is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 67 times (27 in the last 7 days), and 1,594 times in total. It ranks #206,837 among datasets by monthly downloads.
LAVE human judgments This repository contains the human judgment data for Improving Automatic VQA Evaluation Using Large Language Models. Details about the data collection process and crowdworker population can be found in our paper, specifically in section 5.2 and appendix A.1. Field
Open mair-lab/lave-human-feedback on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.