bug: quality scorer-robust score parsing #1165
Closed
Conversation
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
The `format_output` method in `QualityScorer` previously parsed scores by splitting the LLM output by newlines and iterating. This approach was brittle and could fail if the LLM included reasoning, explanations, or extra newlines before the score list, causing valid scores to be missed. This commit refactors the parsing logic to use `re.findall`. This robustly extracts all lines matching the score format from the entire output, regardless of their position. Key improvements: - Resilience: Correctly parses scores even when they are preceded by reasoning or other text from the LLM. - Reliability: Ensures the `scores` list is correctly padded with `None` if fewer scores are found than expected, maintaining a consistent output shape.
for more information, see https://pre-commit.ci
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Improve robustness of score parsing
The
format_outputmethod inQualityScorerpreviously parsed scores by splitting the LLM output by newlines and iterating. This approach was brittle and could fail if the LLM included reasoning, explanations, or extra newlines before the score list, causing valid scores to be missed.This commit refactors the parsing logic to use
re.findall. This robustly extracts all lines matching the score format from the entire output, regardless of their position.Key improvements:
scoreslist is correctly padded withNoneif fewer scores are found than expected, maintaining a consistent output shape.