feat(eval): add zero-shot text classification evaluator#387
Merged
Conversation
Contributor
Author
|
@microsoft-github-policy-service agree [company="Microsoft"] |
jeon185
force-pushed
the
feat/eval-zero-shot-classification
branch
from
14af807 to
96d9ca1
Compare
zhenchaoni
reviewed
Apr 24, 2026
jeon185
force-pushed
the
feat/eval-zero-shot-classification
branch
from
96d9ca1 to
0d93fb9
Compare
jeon185
force-pushed
the
feat/eval-zero-shot-classification
branch
from
0d93fb9 to
7828bfc
Compare
zhenchaoni
approved these changes
Apr 29, 2026
zhenchaoni
left a comment
zhenchaoni
left a comment
Member
There was a problem hiding this comment.
Reviewed the code and validated locally on my device
zhenchaoni
approved these changes
Apr 30, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Resolves #325.
Adds
WinMLZeroShotClassificationEvaluator, registered under thezero-shot-classificationtask, with a pipeline subclass that pads tomax_lengthfor static-shape ONNX.Accuracy and macro-F1 are computed via a new
ClassificationMetric, since HF evaluate has no wrapper for this task.Default dataset is AG News; an E2E entry for
MoritzLaurer/DeBERTa-v3-base-mnli-fever-anliis included.Unit tests cover the evaluator and the metric. An integration test (slow/network) runs end-to-end on DistilBERT, RoBERTa, and DeBERTa NLI checkpoints.