Table 4. System evaluation results by domain experts.
| Informativeness | Key generation | Distractor generation | |
|---|---|---|---|
| Evaluator 1 | 8.5 | 7.5 | 6.5 |
| Evaluator 2 | 7.5 | 4 | 9.5 |
| Evaluator 3 | 8.5 | 9.5 | 9 |
| Evaluator 4 | 9.5 | 8 | 7.5 |
| Evaluator 5 | 8.5 | 7.5 | 8.5 |
| Evaluator 6 | 9 | 9.5 | 9 |
| Evaluator 7 | 8.5 | 6 | 7.5 |
| Evaluator 8 | 8.5 | 9 | 9.5 |
| Evaluator 9 | 7.5 | 6.5 | 5.5 |
| Evaluator 10 | 7 | 9.5 | 7.5 |
| Percentage | 83 | 77 | 80 |