OpenBookQA is a new kind of question-answering dataset modeled after open book exams for assessing human understanding of a subject. It consists of 5,957 multiple-choice elementary-level science questions (4,957 train, 500 dev, 500 test), which probe the understanding of a small “book” of 1,326 core science facts and the application of these facts to novel situations. For training, the dataset includes a mapping from each question to the core science fact it was designed to probe. Answering OpenBookQA questions requires additional broad common knowledge, not contained in the book. The questions, by design, are answered incorrectly by both a retrieval-based algorithm and a word co-occurrence algorithm. Strong neural baselines achieve around 50% on OpenBookQA, leaving a large gap to the 92% accuracy of crowd-workers.
Additionally, we provide 5,167 crowd-sourced common knowledge facts, and an expanded version of the train/dev/test questions where each question is associated with its originating core fact, a human accuracy score, a clarity score, and an anonymized crowd-worker ID (in the “Additional” folder).
Details | Created | Accuracy |
---|---|---|
1 MVP-Tuning Ensemble SenseTime & CUHK | 11/21/2022 | 95% |
2 X-Reasoner HFL & iFLYTEK Research | 7/25/2022 | 94% |
3 Anonymous Anonymous | 1/12/2023 | 92% |
4 GenMC (ensemble) NanJing University (Zixian Huang, Ao Wu, Jiaying Zhou, Yu Gu, Yue Zhao, Gong Cheng) | 4/11/2022 | 92% |
4 Anonymous Anonymous | 12/2/2022 | 92% |