Open
Conversation
Documents how negative tokens bleed into context and can be counterproductive when instructing LLMs. Co-authored-by: openhands <openhands@all-hands.dev>
Fixes negative-bleedthrough by reframing negative instructions as positive descriptions of the desired outcome. Co-authored-by: openhands <openhands@all-hands.dev>
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 a new pattern that fixes negative-bleedthrough by reframing prompts to avoid negation entirely.
Pattern: Point the Target
Problem: Negative instructions activate unwanted concepts in context (see: negative-bleedthrough). The fix isn't "be more specific" since being specific can involve more negation, instead the fix it's choosing which concepts to activate.
Key example (the moon):
Adds relationship:
patterns/point-the-target-> solves->obstacles/negative-bleedthrough