ResearchBenchmarksDiscrimination between Good Faith and Problematic agents (Summarization) on Multi-News 9.0:1Follow6.55Cohen's dTVD-MI0.29961.92233.5455.1677Aug 7, 2025Evaluation ResultsMethodMethodLinksCohen's dTVD-MI2025.086.55JudgeReference availability...Reference availability=ref2025.084.06GPPM2025.082.7MI (DoE)2025.081.53Baseline2025.080.88JudgeReference availability...Reference availability=no ref2025.080.54