Added examples
Browse files
app.py
CHANGED
|
@@ -165,6 +165,7 @@ with gr.Blocks() as demo:
|
|
| 165 |
- Requires models that expose **top-n token log-probabilities** (e.g., OpenAI, DeepSeek, Groq).
|
| 166 |
- Scores are **only comparable when using the same judge model**.
|
| 167 |
|
|
|
|
| 168 |
## 📖 Citation
|
| 169 |
```bibtex
|
| 170 |
@article{pramanick2024spiqa,
|
|
|
|
| 165 |
- Requires models that expose **top-n token log-probabilities** (e.g., OpenAI, DeepSeek, Groq).
|
| 166 |
- Scores are **only comparable when using the same judge model**.
|
| 167 |
|
| 168 |
+
|
| 169 |
## 📖 Citation
|
| 170 |
```bibtex
|
| 171 |
@article{pramanick2024spiqa,
|