ResearchBenchmarksAgent Discrimination on SamSum 4.8:1Agent Discrimination on SamSum 4.8:1Follow6.14Cohen's dTVD-MI-0.13121.49693.1254.7531Aug 7, 2025Evaluation resultsMethodMethodLinksCohen's dTVD-MI2025.086.14JudgeReference availability...Reference availability=ref2025.082.7MI (DoE)2025.082.52GPPM2025.082.52JudgeReference availability...Reference availability=no ref2025.080.54Baseline2025.080.11