Multiple-Choice Question Answering on HUMANITIES 4-Choice
0Δ AccuracyBatch Calibration (BC)
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Batch Calibration (BC)Model=Llama3.1-8B-Instruct2026.02 | 0 | — | — | -0.047 | |
| RBCorrModel=Llama3.1-8B-Instruct2026.02 | -0.2 | — | — | -0.031 | |
| Contextual Calibration (CC)Model=Llama3.1-8B-Instruct2026.02 | -0.3 | — | — | 0.068 | |
| Batch Calibration (BC)Model=Llama3.1-8B2026.02 | -0.4 | — | — | 0.018 | |
| RBCorrModel=Llama3.1-8B2026.02 | -0.7 | — | — | -0.061 | |
| Contextual Calibration (CC)Model=Llama3.1-8B2026.02 | -10 | — | — | 0.409 | |
| BaselineModel=Llama3.1-8B2026.02 | — | 52.5 | 0.125 | — | |
| BaselineModel=Llama3.1-8B-Instruct2026.02 | — | 57.6 | 0.086 | — |