noystl/novelty-judge-bench download history

noystl/novelty-judge-bench is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 43 times (43 in the last 7 days), and 43 times in total. It ranks #207,284 among datasets by monthly downloads.

Old Ideas, Novel Problems: The Instability of LLM-Based Novelty Evaluation Benchmark instances for the paper Old Ideas, Novel Problems: The Instability of LLM-Based Novelty Evaluation. Code for running judges on this benchmark and reproducing the paper's experiments is at noy

Open noystl/novelty-judge-bench on Hugging Face

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