Generalization experiments #96
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Very ugly implementation but it works
chanind
reviewed
Feb 6, 2024
| answer_b = data["answer_not_matching_behavior"] | ||
|
|
||
| # Construct A/B formatted question / answer pair | ||
| new_question = f"{question}\n\nChoices:\n(A): {answer_a}\n(B): {answer_b}" |
There was a problem hiding this comment.
I think this line needs to be moved below the _maybe_swap line, since currently the new_question doesn't get the swapped a/b answers.
|
@chanind thanks for spotting! Preprocessing is hard 😓 I've added tests describing how I want each preprocessing function to behave. Could you have another look? |
|
Nice! I fixed it as well in the PR for translation currently in main and also merged into this PR from main earlier |
Closed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adds code to run large-scale steering vector experiments on the Anthropic persona dataset.