TruthfulQA

TruthfulQA is a benchmark to measure whether a language model is truthful in generating answers to questions. The benchmark comprises 817 questions that span 38 categories, including health, law, finance and politics. Questions are crafted so that some humans would answer falsely due to a false belief or misconception. To perform well, models must avoid generating false answers learned from imitating human texts. The text in the dataset is in English. The associated BCP-47 code is en. Note: Both generation and multiplechoice configurations have the same questions. An example of generation looks as follows: An example of multiplechoice looks as follows: - type: A string denoting whether the…