Natural Language Explanation Generation on HealthVer (test)
0.033Faithfulness
CLUE-Span+Steering
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2025.05 | 0.033 | 0.44 | 0.53 | 0.8 | |
2025.05 | 0.021 | 0.39 | 0.5 | 0.85 | |
2025.05 | 0.02 | 0.23 | 0.77 | 0.68 | |
2025.05 | 0.007 | 0.34 | 0.59 | 0.82 | |
2025.05 | 0.006 | 0.33 | 0.68 | 0.75 | |
2025.05 | 0.005 | 0.1 | 0.83 | 0.61 | |
2025.05 | -0.028 | - | - | 0.74 | |
2025.05 | -0.1 | - | - | 0.55 | |
2025.05 | -0.105 | - | - | 0.66 |