Improving language model behavior by training on a curated dataset

2021-06-10来源 OpenAI BlogEnglish
Our latest research finds we can improve language model behavior with respect to specific behavioral values by fine-tuning on a small, curated dataset.

原文：https://www.a8q9.cn/en/article/improving-language-model-behavior-by-training-on-a-curated-dataset-a34552.html

相关文章