List your company

Multiple-Choice Question Answering on SOCIAL SCI. 4-Choice

0.5ΔAccBatch Calibration (BC)
-14.58-10.665-6.75-2.835Feb 12, 2026

Evaluation results

MethodLinks
Batch Calibration (BC)Model=Llama3.1-8B-Instruct2026.020.5——-0.006
RBCorrModel=Llama3.1-8B-Instruct2026.020.3——0.004
Batch Calibration (BC)Model=Llama3.1-8B2026.020——0.037
RBCorrModel=Llama3.1-8B2026.02-0.3——0.04
Contextual Calibration (CC)Model=Llama3.1-8B-Instruct2026.02-1——0.09
Contextual Calibration (CC)Model=Llama3.1-8B2026.02-14——0.348
BaselineModel=Llama3.1-8B2026.02—69.70.038—
BaselineModel=Llama3.1-8B-Instruct2026.02—72.60.021—