Multiple-Choice Question Answering on OTHERS 4-Choice
0Delta AccBatch Calibration (BC)
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Batch Calibration (BC)Model=Llama3.1-8B-Instruct2026.02 | 0 | — | — | 0.004 | |
| RBCorrModel=Llama3.1-8B-Instruct2026.02 | 0 | — | — | 0.013 | |
| RBCorrModel=Llama3.1-8B2026.02 | -0.3 | — | — | -0.009 | |
| Contextual Calibration (CC)Model=Llama3.1-8B-Instruct2026.02 | -0.7 | — | — | 0.073 | |
| Batch Calibration (BC)Model=Llama3.1-8B2026.02 | -0.7 | — | — | 0.007 | |
| Contextual Calibration (CC)Model=Llama3.1-8B2026.02 | -9.5 | — | — | 0.259 | |
| BaselineModel=Llama3.1-8B2026.02 | — | 68.3 | 0.081 | — | |
| BaselineModel=Llama3.1-8B-Instruct2026.02 | — | 71.5 | 0.025 | — |