ggbetz/belcy-eval-logs download history
ggbetz/belcy-eval-logs is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 185 times (30 in the last 7 days), and 185 times in total. It ranks #95,025 among datasets by monthly downloads.
BelCy evaluation logs Map manifests and Inspect logs of every run in the technical report "Do Language Model Credences Follow the Argument? A Bayesian Benchmark for Belief Consistency (BelCy)" (Gregor Betz, in preparation). The evaluation code is logikon-ai/belcy-eval (doi:10.5281/zen
Open ggbetz/belcy-eval-logs on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.