Update Groundedness Evaluator to support multi-turn evaluation#4942
Merged
Conversation
Test Results for assets-test92 tests 92 ✅ 2s ⏱️ Results for commit 97e8668. ♻️ This comment has been updated with latest results. |
…#4957) Data-driven prompt improvements validated on 300 FaithDial traces: - Added 5-step evaluation procedure with tool-result parsing guidance - Introduced 'substantive hallucination' vs 'NOT hallucination' taxonomy - Added score-4 example showing tool-call + paraphrase pattern - Tightened score-3 to require zero factual propositions - Added CRITICAL rule: any substantive hallucination -> score <= 2 Results (v1 -> v5): - gpt-5.4-mini: 76.3% -> 83.7% accuracy, F1 88.2% - gpt-5.4: 65.7% -> 79.7% accuracy, F1 83.1% Co-authored-by: Ali Mahmoudzadeh <amah@microsoft.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
lykelly19
approved these changes
Apr 24, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Updated the eval to support multi turn.
multiturn quality report: https://msdata.visualstudio.com/Vienna/_git/evaluators?path=/experiments/evaluator_quality_analysis/reports/azure_mt_evaluator_quality_report.md&_a=preview