List your company

Multiple-Choice Question Answering on HUMANITIES 4-Choice

0Δ AccuracyBatch Calibration (BC)
-10.4-7.7-5-2.3Feb 12, 2026

Evaluation results

MethodLinks
Batch Calibration (BC)Model=Llama3.1-8B-Instruct2026.020——-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—52.50.125—
BaselineModel=Llama3.1-8B-Instruct2026.02—57.60.086—