Hendrycks, Dan, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. “Measuring massive multitask language understanding,” 2021. https://arxiv.org/abs/2009.03300.
We propose a new test to measure a text model’s multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more. To attain high accuracy on this test, models must possess extensive world knowledge and problem solving ability.
By comprehensively evaluating the breadth and depth of a model’s academic and professional understanding, our test can be used to analyze models across many tasks and to identify important shortcomings.
Our expansive test can help researchers pinpoint important shortcomings of models, making it easier to gain a clearer picture of state-of-the-art capabilities.
- Format Sensitivity