Training language models to follow instructions with human feedback
通过人类反馈的微调，在广泛的任务中使语言模型与用户的意图保持一致
aligning language models with user intent on a wide range of tasks by fine-tuning
with human feedback
实验动机
language models to be helpful (they should help the user solve their task), honest (they shouldn’t fabricate information or mislead the user), and harmless (they should not cause physical, psychological, or social harm to people or the environment).
实验过程
- 我们首先聘请了一个由40名承包商组成的团队，根据他们在筛选测试中的表现，为我们的数据贴上标签（详见3.4节和附录B.1）。
- We then collect a dataset of human-written demonstrations of the
desired output behavior on (mostly English) prompts submitted to
the OpenAI API3 and some labeler-written prompts - we collect a dataset of human-labeled comparisons between
outputs from our models on a larger set of API prompts. - We then train a reward model (RM) on this dataset to predict
which model output our labelers would prefer. - Finally, we use this RM as a reward function and fine-tune our supervised learning baseline to maximize this reward using the PPO algorithm (Schulman et al., 2017).
