Reading Comprehension on BoolQ (Perf., Sp.)
85.3AccuracyBest Model
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Best ModelBackbone=LLaMA 3.1 8B, Shots=5-shot, #D=42025.10 | 85.3 | 1.11 | |
| BSBABackbone=LLaMA 3.1 8B, Shots=5-shot, #D=62025.10 | 83 | 1.22 | |
| BaselineBackbone=LLaMA 3.1 8B, Shots=5-shot2025.10 | 82.7 | — |