ResearchBenchmarksDiscrimination between Good Faith and Problematic agents (Summarization) on BillSum 9.3:1Follow5.91Cohen's dTVD-MI-0.071.48253.0354.5875Aug 7, 2025Evaluation ResultsMethodMethodLinksCohen's dTVD-MI2025.085.91JudgeReference availability...Reference availability=ref2025.084.23GPPM2025.083.59MI (DoE)2025.082.24Baseline2025.080.91JudgeReference availability...Reference availability=no ref2025.080.16