Skip to content

Commit 5f4d586

Browse files
jsondaicopybara-github
authored andcommitted
fix: Fix typos in evaluation example metric prompt templates.
PiperOrigin-RevId: 676917898
1 parent 2b84142 commit 5f4d586

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

vertexai/evaluation/metrics/_default_templates.py

+2-2
Original file line numberDiff line numberDiff line change
@@ -390,7 +390,7 @@
390390
391391
## Evaluation Steps
392392
STEP 1: Analyze Response A based on the instruction following criteria: Determine how well Response A fulfills the requirements outlined in the instructions and provide assessment according to the criterion.
393-
STEP 2: Analyze Response B based on the instruction following criteria: Determine how well Response A fulfills the requirements outlined in the instructions and provide assessment according to the criterion.
393+
STEP 2: Analyze Response B based on the instruction following criteria: Determine how well Response B fulfills the requirements outlined in the instructions and provide assessment according to the criterion.
394394
STEP 3: Compare the overall performance of Response A and Response B based on your analyses and assessment.
395395
STEP 4: Output your preference of "A", "SAME" or "B" to the pairwise_choice field according to the Rating Rubric.
396396
STEP 5: Output your assessment reasoning in the explanation field.
@@ -900,7 +900,7 @@
900900
901901
## Evaluation Steps
902902
STEP 1: Analyze Response A based on the question answering quality criteria: Determine how well Response A fulfills the user requirements, is grounded in the context, is complete and fluent, and provides assessment according to the criterion.
903-
STEP 2: Analyze Response B based on the question answering quality criteria: Determine how well Response A fulfills the user requirements, is grounded in the context, is complete and fluent, and provides assessment according to the criterion.
903+
STEP 2: Analyze Response B based on the question answering quality criteria: Determine how well Response B fulfills the user requirements, is grounded in the context, is complete and fluent, and provides assessment according to the criterion.
904904
STEP 3: Compare the overall performance of Response A and Response B based on your analyses and assessment.
905905
STEP 4: Output your preference of "A", "SAME" or "B" to the pairwise_choice field according to the Rating Rubric.
906906
STEP 5: Output your assessment reasoning in the explanation field.

0 commit comments

Comments
 (0)