ChatGPT - InstructGPT 论文简读

Posted 2023-02-14 SpikeKing

发表于NLP会议：NeurlPS，EMNLP

• EMNLP: Empirical Methods in Natural Language Processing，自然语言处理中的经验方法
• NeurlPS: Neural Information Processing Systems，神经信息处理系统

ChatGPT: Optimizing Language Models for Dialogue，优化对话的语言模型

• ChatGPT：https://openai.com/blog/chatgpt/
• GPT：Generative Pre-trained Transformer，生成式预训练Transformer

We’ve trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer followup questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests. ChatGPT is a sibling model to InstructGPT, which is trained to follow an instruction in a prompt and provide a detailed response.

• 我们已经训练了一个名