Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

COT 方法应该是Multi-Stage吧 #5

Closed
cobraheleah opened this issue May 10, 2023 · 4 comments
Closed

COT 方法应该是Multi-Stage吧 #5

cobraheleah opened this issue May 10, 2023 · 4 comments
Labels
question Further information is requested

Comments

@cobraheleah
Copy link

COT(Chain of thought prompting elicits reasoning in large language models)这篇文章应该是Prompt Engineering的Multi-Stage方法吧,我看归类到了Single-Stage下面

@GoooDte
Copy link
Collaborator

GoooDte commented May 10, 2023

您好,single-stage和multi-stage的划分标准本质上是once input-output和multi-times input-output,CoT本质上还是模型一次输入输出完成的,因此是single-stage类的方法

@cobraheleah
Copy link
Author

不好意思,之前写错了,应该是zero-COT(Large Language Models are Zero-Shot Reasoners)这篇文章,它是通过两阶段的input-output得到最终的结果,应该是Multi-Stage方法吧,我看归类到了Single-Stage下面

@GoooDte
Copy link
Collaborator

GoooDte commented May 12, 2023

感谢您的问题!我们当时关注的是他生成rationale的步骤 至于答案获取的步骤通过做实验可以发现其实是不需要的 它只是为了让模型能够按照特定的格式生成答案(看论文中的例子也可以知道) 所以索性把它归到了single-stage 因为它的两个阶段跟multi-stage类的论文相比不太具有代表性

@cobraheleah
Copy link
Author

好的,感谢,明白了

@zxlzr zxlzr closed this as completed May 15, 2023
@zxlzr zxlzr added the question Further information is requested label May 15, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

3 participants