Natural Language Inference Explanation Evaluation on SICK (sample)
95.63Average ScoreMorphNLI
Evaluation Results
| Method | Links | |
|---|---|---|
| MorphNLIevaluation_target=morphism quality only2025.02 | 95.63 | |
| MorphNLIevaluation_target=modular approach explanations2025.02 | 70.63 | |
| GPT-4oevaluation_target=standard explanations2025.02 | 62.5 | |
| Llama 3.1 8Bevaluation_target=standard explanations2025.02 | 47.5 |