Can we predict the kinds of domains and tasks for which large generative models are more likely to be robust (or not robust), and how does this relate to the training data? Are there techniques we can use to predict and mitigate worst-case behavior?
Created by Docbot version v3
Comments:
No comments found
We track editorial changes to analyses and updates to a point's status and display the previous versions here as part of an effort to promote transparency regarding our curation process. Unfortunately, for this point, due to how it was stored in our database, there are no previous versions available for display.