HW1: HC3 AI-Generated Text Detector
Fine-tuned sentence-transformers/all-MiniLM-L6-v2 for binary classification of HC3 answers (0 = human, 1 = ChatGPT). Trained for 5 epochs with AdamW (lr = 2e-5), batch size 32, and max length 256.
Results (HC3 test set, 4,668 answers)
| Model | Test Accuracy |
|---|---|
| Baseline: frozen embeddings + logistic regression | 0.8449 |
| Fine-tuned (this model) | 0.9856 |
Limitations
Trained on a historical benchmark (late-2022 ChatGPT). This model is not a reliable detector for current AI-generated text.
- Downloads last month
- 29
Model tree for slmyu0915/hw1-hc3-detector
Base model
nreimers/MiniLM-L6-H384-uncased Quantized
sentence-transformers/all-MiniLM-L6-v2