WinoWhat: A Parallel Corpus of Paraphrased WinoGrande Sentences with Common Sense Categorization
收藏资源简介：
This is the dataset accompanying the paper "WinoWhat: A Parallel Corpus of Paraphrased WinoGrande Sentences withCommon Sense Categorization". In this work, we evaluate LLMs' performance on Winograd Schema Challenges by paraphrasing the validation set of WinoGrande. We provide each instance with common sense category annotations. The dataset structure is as follows:sentence: the original text as it appears in WinoGrandeparaphrased_sentence: the paired paraphrased textoption1 and option2: the two possible antecedents that can be filled in the _-tokenanswer: the correct optiongpt_category and gpt_category_names: the numerical and string representation of the common sense category/ categories attributed to the textin_original_experiment: whether this row was included in the original experiments or not
