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

Question: using LIME for text generation #747

Open
dyomed93 opened this issue May 30, 2024 · 2 comments
Open

Question: using LIME for text generation #747

dyomed93 opened this issue May 30, 2024 · 2 comments

Comments

@dyomed93
Copy link

Good evening,
is it possible to use LIME for text generation tasks? Or only for classification?
Thanks

@spook95
Copy link

spook95 commented May 30, 2024 via email

@ShaileshSridhar2403
Copy link

Most text generation is carried via classification of tokens, with a probability score for each token based on how likely it is to be the correct token at that position. You should be able to hence use LIME just as you would use it normally, and get a feature importance score for every token generated

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