MAINT: Add pre-release scorer evaluation metrics#1626
Merged
adrian-gavrila merged 1 commit intomicrosoft:mainfrom Apr 17, 2026
Merged
Conversation
Update scorer eval metrics JSONL files with results from the pre-release scorer evaluation run across harm categories, objective achievement, and refusal scorers. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Updates the scorer evaluation metrics JSONL files with results from the latest pre-release evaluation run. New metric entries are
appended for the following scorers across the existing eval datasets:
These are data-only additions intended to capture baseline scorer performance ahead of the upcoming release. No code changes are included.
Tests and Documentation
No code changes — only appended JSONL metrics records produced by the existing scorer evaluation pipeline. Existing tests remain
valid; no documentation updates required. JupyText was not run as no notebooks or code samples were modified.