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

情景问答对 #12

Open
VaTyc opened this issue May 6, 2023 · 5 comments
Open

情景问答对 #12

VaTyc opened this issue May 6, 2023 · 5 comments

Comments

@VaTyc
Copy link

VaTyc commented May 6, 2023

利用ChatGPT联想生成具体的情景问答,能够百分百确定生成的法律依据没有错误吗

@Bolozano
Copy link
Collaborator

Bolozano commented May 6, 2023

可以的,可惜我们的这一版生成的训练数据可能初始法律清洗的不够干净,有些分点的法律没有归纳好。如果用我们后来整理的9k条核心法律一对一的生成数据(我们在测试集上这样做的),可以确保至少生成的法律依据百分百没有问题。

@VaTyc
Copy link
Author

VaTyc commented May 6, 2023

如果是一对一的生成数据,那应该生成的问答对只是适用于当前用于生成的法律条款的,但是我看见例子里面还涉及到了其他的法律条款,请问这种是怎么处理的呢?

@Bolozano
Copy link
Collaborator

Bolozano commented May 7, 2023

之前生成数据集的时候考虑到很多法条有前后文补充关系,所以都是取了临近的几条法律生成样本。如果需要单条法条的,可以参考我们的测试集,在data/核心法条9k_测试5k里。

@robblecrunch
Copy link

分点的规纳, 只有靠规则了。

@robblecrunch
Copy link

这个生成的指令, 可分享吗?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants