Handle missing verdicts in Faithfulness eval #612
Merged
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Outdated suggestions cannot be applied.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.
Description:
The
count_verified_statements
method currently fails with an undefined method 'captures' for nil error when the expected string "Final verdict for each statement in order:" is absent from the LLMs response. This typically occurs if the provided context is either blank or not relevant to the question/answer.Proposed Change:
This pull request introduces a guard clause in the
count_verified_statements
method to handle cases where the LLMs output does not contain the expected verdict format. I think returning a score of0.0
makes sense given that this would be the correct score in most of these failure cases.Code Changes:
0.0
immediately if no match is found in the verifications string.