GitHub / hitz-zentroa / This-is-not-a-Dataset

We introduce a large semi-automatically generated dataset of ~400,000 descriptive sentences about commonsense knowledge that can be true or false in which negation is present in about 2/3 of the corpus in different forms that we use to evaluate LLMs

JSON API: https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hitz-zentroa%2FThis-is-not-a-Dataset

Topics: benchmark, common-sense, commonsense, decoder, huggingface, llama, llama2, llm, llm-inference, negation, scorer, transformer

Files