Distractor Generation on CLOTH Easy
0Invalid RatioQwen 2.5 7B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen 2.5 7Btraining=DCDG-trained2025.11 | 0 | |
| Gemma 2 9Btraining=DCDG-trained2025.11 | 0.2 | |
| Llama 3.1 8Btraining=DCDG-trained2025.11 | 0.2 | |
| GPT-4oprompting=5-shot2025.11 | 1.6 | |
| GPT-4oprompting=0-shot2025.11 | 6.8 |