Improving Short Text Classification With Augmented Data Using GPT-3
This addresses the problem of data scarcity for researchers using GPT-3 in short text classification, though it is incremental as it builds on existing GPT-3 capabilities.
The study tackled the issue of GPT-3 requiring high-quality or large training sets for short text classification by augmenting a small dataset with GPT-3-generated examples, resulting in improved classification performance with up to 80% validation accuracy and more consistent accuracy on unseen data.
GPT-3 is a large-scale natural language model developed by OpenAI that can perform many different tasks, including topic classification. Although researchers claim that it requires only a small number of in-context examples to learn a task, in practice GPT-3 requires these training examples to be either of exceptional quality or a higher quantity than easily created by hand. To address this issue, this study teaches GPT-3 to classify whether a question is related to data science by augmenting a small training set with additional examples generated by GPT-3 itself. This study compares two classifiers: the GPT-3 Classification Endpoint with augmented examples, and the GPT-3 Completion Endpoint with an optimal training set chosen using a genetic algorithm. We find that while the augmented Completion Endpoint achieves upwards of 80 percent validation accuracy, using the augmented Classification Endpoint yields more consistent accuracy on unseen examples. In this way, giving large-scale machine learning models like GPT-3 the ability to propose their own additional training examples can result in improved classification performance.