Model Card for Model ID
Results
| Model | Test Accuracy |
|---|---|
| Frozen sentence-embedding baseline (Logistic Regression) | 0.8449 |
Fine-tuned sentence-transformers/all-MiniLM-L6-v2 classifier |
0.9970 |
The fine-tuned model was trained on the HC3 human-vs.-ChatGPT answer classification task. Results were evaluated on the held-out test split.
- Downloads last month
- 8