Question Answering Sufficiency Prediction on CouldAsk Benchmark
0.7878BBC ScoreIdentify-then-Verify
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Identify-then-Verify2025.12 | 0.7878 | 0.6848 | 0.6965 | 0.7846 | 0.8333 | 0.695 | |
| MIGRES2025.12 | 0.6691 | 0.5636 | 0.5815 | 0.7703 | 0.8182 | 0.821 | |
| Autorater2025.12 | 0.6389 | 0.6181 | 0.5949 | 0.6793 | 0.8065 | 0.8287 |