String-level response similarity on RA-QA Single-Verify, Discriminative tasks
94BERTScoreRAMoEA-QA
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| RAMoEA-QA2026.03 | 94 | 92.64 | |
| CareAQA-operaGTBackbone=OPERA-GT2026.03 | 91 | 89.95 | |
| CareAQA-operaCTBackbone=OPERA-CT2026.03 | 87 | 86.08 | |
| PENGI2026.03 | 3 | 4.11 |