Arithmetic Reasoning on ARITH 2-Choice
12.4Δ AccuracyRBCorr
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| RBCorrModel=Llama3.1-8B, Few-shot prompt format=Yes2026.02 | 12.4 | — | — | -0.194 | |
| Batch Calibration (BC)Model=Llama3.1-8B, Few-shot prompt format=Yes2026.02 | 12.1 | — | — | -0.086 | |
| Contextual Calibration (CC)Model=Llama3.1-8B, Few-shot prompt format=Yes2026.02 | 11.8 | — | — | -0.182 | |
| RBCorrModel=Llama3.1-8B-Instruct, Few-shot prompt format=Yes2026.02 | 5.8 | — | — | -0.151 | |
| Batch Calibration (BC)Model=Llama3.1-8B-Instruct, Few-shot prompt format=Yes2026.02 | 5.2 | — | — | -0.09 | |
| Contextual Calibration (CC)Model=Llama3.1-8B-Instruct, Few-shot prompt format=Yes2026.02 | 3.2 | — | — | -0.058 | |
| BaselineModel=Llama3.1-8B, Few-shot prompt format=Yes2026.02 | — | 74.2 | 0.203 | — | |
| BaselineModel=Llama3.1-8B-Instruct, Few-shot prompt format=Yes2026.02 | — | 78.8 | 0.159 | — |