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

Editing non-QA knowledge, such as DUNE dataset. #118

Open
quqxui opened this issue Dec 21, 2023 · 1 comment
Open

Editing non-QA knowledge, such as DUNE dataset. #118

quqxui opened this issue Dec 21, 2023 · 1 comment
Assignees
Labels
enhancement New feature or request

Comments

@quqxui
Copy link

quqxui commented Dec 21, 2023

Hi,

Thank you for your valuable open source contributions! I would like to inquire about how to utilize your toolkit for editing reasoning and non-QA knowledge.

For instance, in the paper titled "DUnE: Dataset for Unified Editing," there is an example that requires editing or injecting knowledge. The scenario is as follows:

  • Knowledge needed to edit or inject:
    In a tiger population, without any male tigers, the females will not be able to mate and produce offspring, making the population die out.
  • Edit Query:
    Some animals are very rare. For example, there are very few Siberian tigers. If the only Siberian tigers left are female, what will most likely happen? A. The females will find another type of male animal to mate with and produce more Siberian tigers. B. The females will mate with each other and produce more Siberian tigers. C. The females will only be able to produce female Siberian tigers. D. The females will not be able to produce more Siberian tigers and they will die out. [Answer: D]

I eagerly await your response!

@XeeKee
Copy link
Collaborator

XeeKee commented Dec 21, 2023

Thank you for your attention. We plan to support this method in February 2024.

@zxlzr zxlzr added the enhancement New feature or request label Dec 21, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

4 participants