论文标题
测量大量的多任务语言理解
Measuring Massive Multitask Language Understanding
论文作者
论文摘要
我们提出了一项新测试，以测量文本模型的多任务精度。该测试涵盖了57项任务，包括基本数学，美国历史，计算机科学，法律等。为了在此测试中获得高精度，模型必须具有广泛的世界知识和解决问题的能力。我们发现，尽管最近的模型几乎具有随机性的准确性，但最大的GPT-3模型平均将随机机会提高了近20个百分点。但是，在57个任务中的每一个中，最佳模型仍需要进行大量改进，才能达到专家级的准确性。模型还具有偏斜的性能，并且经常不知道何时错了。更糟糕的是，他们在某些社会重要的主题（例如道德和法律）上仍然具有几乎随机的准确性。通过全面评估模型的学术和专业理解的广度和深度，我们的测试可用于分析许多任务的模型并确定重要的缺点。
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. We find that while most recent models have near random-chance accuracy, the very largest GPT-3 model improves over random chance by almost 20 percentage points on average. However, on every one of the 57 tasks, the best models still need substantial improvements before they can reach expert-level accuracy. Models also have lopsided performance and frequently do not know when they are wrong. Worse, they still have near-random accuracy on some socially important subjects such as morality and law. 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.
