To precisely evaluate a language model's capability for logical reading comprehension, we present a dataset for testing the understanding of the rationale behind critical reasoning. For questions taken from an existing multiplechoice logical reading comprehension dataset, we crowdsource rationale texts that explain why we should select or eliminate answer options, resulting in 3,003 multiple-choice subquestions that are associated with 943 main questions. Experiments on our dataset show that recent large language models (e.g., InstructGPT) struggle to answer the subquestions even if they are able to answer the main questions correctly. We find that the models perform particularly poorly in answering subquestions written for the incorrect options of the main questions, implying that the models have a limited capability for explaining why incorrect alternatives should be eliminated. These results suggest that our dataset encourages further investigation into the critical reasoning ability of language models while focusing on the elimination process of relevant alternatives.

If your child isn't a straight-A student today, don't worry, take the long view. In the future, artificial intelligence (AI) will automate many jobs and disrupt industries, outperforming people in many areas. In generations prior, college degrees and post-graduate degrees were a path toward having careers with higher than average income-earning potential. Automation due to AI will impact both white collar and blue collar jobs alike. Presently AI is already beginning to make inroads in the areas of medicine, legal, marketing, customer service, bookkeeping, financial services, business analytics, transportation, publishing, and others.