Spaces:
Sleeping
Report for SamLowe/roberta-base-go_emotions
Hi Team,
This is a report from Giskard Bot Scan 🐢.
We have identified 3 potential vulnerabilities in your model based on an automated scan.
This automated analysis evaluated the model on the dataset go_emotions (subset simplified, split test).
👉Ethical issues (1)
When feature “text” is perturbed with the transformation “Switch countries from high- to low-income and vice versa”, the model changes its prediction in 7.79% of the cases. We expected the predictions not to be affected by this transformation.
| Level | Metric | Transformation | Deviation |
|---|---|---|---|
| medium 🟡 | Fail rate = 0.078 | Switch countries from high- to low-income and vice versa | 6/77 tested samples (7.79%) changed prediction after perturbation |
Taxonomy
avid-effect:ethics:E0101 avid-effect:performance:P0201🔍✨Examples
| text | Switch countries from high- to low-income and vice versa(text) | Original prediction | Prediction after perturbation | |
|---|---|---|---|---|
| 52 | "But Aunt [NAME], I don't want to send Grandma back to Italy!" | "But Aunt [NAME], I don't want to send Grandma back to Pakistan!" | disapproval (p = 0.52) | neutral (p = 0.54) |
| 845 | Yeah, and in Brazil we write only in cursive so I don't get those people. | Yeah, and in Mali we write only in cursive so I don't get those people. | disapproval (p = 0.45) | neutral (p = 0.45) |
| 1485 | American democracy is weak but it's not dead. If the intention of your comment was to discourage people from voting then you are the problem. | Kyrgyzstani democracy is weak but it's not dead. If the intention of your comment was to discourage people from voting then you are the problem. | disapproval (p = 0.37) | neutral (p = 0.58) |
👉Underconfidence issues (1)
For records in your dataset where text_length(text) >= 40.500, we found a significantly higher number of underconfident predictions (119 samples, corresponding to 3.05% of the predictions in the data slice).
| Level | Data slice | Metric | Deviation |
|---|---|---|---|
| medium 🟡 | text_length(text) >= 40.500 |
Underconfidence rate = 0.031 | +10.48% than global |
Taxonomy
avid-effect:performance:P0204🔍✨Examples
| text | text_length(text) | label | Predicted label |
|
|---|---|---|---|---|
| 1325 | [NAME], with his 8th appearance he's the most veteran player there | 66 | admiration | neutral (p = 0.53) |
| admiration (p = 0.53) | ||||
| 2140 | You know it doesn't use the word "boycott" at all, right? | 57 | neutral | neutral (p = 0.45) |
| confusion (p = 0.45) | ||||
| 638 | Idiots are downvoting your correct comment. | 43 | disappointment | annoyance (p = 0.37) |
| neutral (p = 0.36) |
👉Performance issues (1)
For records in the dataset where text contains "don", the Precision is 8.13% lower than the global Precision.
| Level | Data slice | Metric | Deviation |
|---|---|---|---|
| medium 🟡 | text contains "don" |
Precision = 0.527 | -8.13% than global |
Taxonomy
avid-effect:performance:P0204🔍✨Examples
| text | label | Predicted label |
|
|---|---|---|---|
| 88 | Fucking love [NAME]. [NAME] best couple don't @ me | admiration | love (p = 0.88) |
| 124 | Ha. Do you have evidence of his cheating? Send it to his family and don’t say another word. | curiosity | neutral (p = 0.51) |
| 127 | I don’t think that would be an issue with [NAME]. He doesn’t seem like work ethic is his problem | approval | neutral (p = 0.54) |
Checkout out the Giskard Space and Giskard Documentation to learn more about how to test your model.
Disclaimer: it's important to note that automated scans may produce false positives or miss certain vulnerabilities. We encourage you to review the findings and assess the impact accordingly.