Skip to content

Possible error in evaluator pass / fail condition #393

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Possible error in evaluator pass / fail condition #393

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a1d121b
Possible error in evaluator pass / fail condition
ShayakSarkar May 24, 2025
20f4108
Removed other possible errors
May 24, 2025
35b5264
Other possible errors
May 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions articles/ai-foundry/concepts/evaluation-evaluators/agent-evaluators.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,7 @@ intent_resolution(

### Intent resolution output

The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score <= threshold, or "fail" otherwise. Using the reason and additional fields can help you understand why the score is high or low.
The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score >= threshold, or "fail" otherwise. Using the reason and additional fields can help you understand why the score is high or low.

```python
{
Expand Down Expand Up @@ -134,7 +134,7 @@ tool_call_accuracy(

### Tool call accuracy output

The numerical score (passing rate of correct tool calls) is 0-1 and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score <= threshold, or "fail" otherwise. Using the reason and tool call detail fields can help you understand why the score is high or low.
The numerical score (passing rate of correct tool calls) is 0-1 and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score >= threshold, or "fail" otherwise. Using the reason and tool call detail fields can help you understand why the score is high or low.

```python
{
Expand Down Expand Up @@ -171,7 +171,7 @@ task_adherence(

### Task adherence output

The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score <= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.
The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score >= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.

```python
{
Expand Down
8 changes: 4 additions & 4 deletions articles/ai-foundry/concepts/evaluation-evaluators/general-purpose-evaluators.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ coherence(

### Coherence output

The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score <= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.
The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score >= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.

```python
{
Expand Down Expand Up @@ -85,7 +85,7 @@ fluency(

### Fluency output

The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score <= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.
The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score >= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.

```python
{
Expand Down Expand Up @@ -124,7 +124,7 @@ qa_eval(

### QA output

While F1 score outputs a numerical score on 0-1 float scale, the other evaluators output numerical scores on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score <= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.
While F1 score outputs a numerical score on 0-1 float scale, the other evaluators output numerical scores on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score >= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.

```python
{
Expand Down Expand Up @@ -161,4 +161,4 @@ While F1 score outputs a numerical score on 0-1 float scale, the other evaluator
## Related content

- [How to run batch evaluation on a dataset](../../how-to/develop/evaluate-sdk.md#local-evaluation-on-test-datasets-using-evaluate)
- [How to run batch evaluation on a target](../../how-to/develop/evaluate-sdk.md#local-evaluation-on-a-target)
- [How to run batch evaluation on a target](../../how-to/develop/evaluate-sdk.md#local-evaluation-on-a-target)
10 changes: 5 additions & 5 deletions articles/ai-foundry/concepts/evaluation-evaluators/rag-evaluators.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@ retrieval(

### Retrieval output

The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (a default is set), we also output "pass" if the score <= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.
The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (a default is set), we also output "pass" if the score >= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.

```python
{
Expand Down Expand Up @@ -160,7 +160,7 @@ document_retrieval_evaluator(retrieval_ground_truth=retrieval_ground_truth, retr

### Document retrieval output

All numerical scores have `high_is_better=True` except for `holes` and `holes_ratio` which have `high_is_better=False`. Given a numerical threshold (default to 3), we also output "pass" if the score <= threshold, or "fail" otherwise.
All numerical scores have `high_is_better=True` except for `holes` and `holes_ratio` which have `high_is_better=False`. Given a numerical threshold (default to 3), we also output "pass" if the score >= threshold, or "fail" otherwise.

```python
{
Expand Down Expand Up @@ -203,7 +203,7 @@ groundedness(

### Groundedness output

The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score <= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.
The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score >= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.

```python
{
Expand Down Expand Up @@ -273,7 +273,7 @@ relevance(

### Relevance output

The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score <= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.
The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score >= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.

```python
{
Expand Down Expand Up @@ -303,7 +303,7 @@ response_completeness(

### Response completeness output

The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score <= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.
The numerical score on a likert scale (integer 1 to 5) and a higher score is better. Given a numerical threshold (default to 3), we also output "pass" if the score >= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.

```python
{
Expand Down
12 changes: 6 additions & 6 deletions ...cles/ai-foundry/concepts/evaluation-evaluators/textual-similarity-evaluators.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,7 @@ similarity(

### Similarity output

The numerical score on a likert scale (integer 1 to 5) and a higher score means a higher degree of similarity. Given a numerical threshold (default to 3), we also output "pass" if the score <= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.
The numerical score on a likert scale (integer 1 to 5) and a higher score means a higher degree of similarity. Given a numerical threshold (default to 3), we also output "pass" if the score >= threshold, or "fail" otherwise. Using the reason field can help you understand why the score is high or low.

```python
{
Expand Down Expand Up @@ -84,7 +84,7 @@ f1_score(

### F1 score output

The numerical score is a 0-1 float and a higher score is better. Given a numerical threshold (default to 0.5), we also output "pass" if the score <= threshold, or "fail" otherwise.
The numerical score is a 0-1 float and a higher score is better. Given a numerical threshold (default to 0.5), we also output "pass" if the score >= threshold, or "fail" otherwise.

```python
{
Expand Down Expand Up @@ -112,7 +112,7 @@ bleu_score(

### BLEU output

The numerical score is a 0-1 float and a higher score is better. Given a numerical threshold (default to 0.5), we also output "pass" if the score <= threshold, or "fail" otherwise.
The numerical score is a 0-1 float and a higher score is better. Given a numerical threshold (default to 0.5), we also output "pass" if the score >= threshold, or "fail" otherwise.

```python
{
Expand Down Expand Up @@ -141,7 +141,7 @@ gleu_score(

### GLEU score output

The numerical score is a 0-1 float and a higher score is better. Given a numerical threshold (default to 0.5), we also output "pass" if the score <= threshold, or "fail" otherwise.
The numerical score is a 0-1 float and a higher score is better. Given a numerical threshold (default to 0.5), we also output "pass" if the score >= threshold, or "fail" otherwise.

```python
{
Expand Down Expand Up @@ -170,7 +170,7 @@ rouge(

### ROUGE score output

The numerical score is a 0-1 float and a higher score is better. Given a numerical threshold (default to 0.5), we also output "pass" if the score <= threshold, or "fail" otherwise.
The numerical score is a 0-1 float and a higher score is better. Given a numerical threshold (default to 0.5), we also output "pass" if the score >= threshold, or "fail" otherwise.

```python
{
Expand Down Expand Up @@ -205,7 +205,7 @@ meteor_score(

### METEOR score output

The numerical score is a 0-1 float and a higher score is better. Given a numerical threshold (default to 0.5), we also output "pass" if the score <= threshold, or "fail" otherwise.
The numerical score is a 0-1 float and a higher score is better. Given a numerical threshold (default to 0.5), we also output "pass" if the score >= threshold, or "fail" otherwise.

```python
{
Expand Down