List your company

Discrimination between Good Faith and Problematic agents (Summarization) on XSum 18.5:1

6.69Cohen's dTVD-MI
-0.55881.32313.2055.0869Aug 7, 2025

Evaluation results

MethodLinks
TVD-MI2025.086.69
JudgeReference availability=ref2025.083.39
GPPM2025.082.85
MI (DoE)2025.081.89
Baseline2025.080.29
JudgeReference availability=no ref2025.08-0.28