ResearchBenchmarksProof By Contradiction on Dl (test)Follow88AccuracyGPT70.3274.9179.584.09Oct 10, 2025Evaluation ResultsMethodMethodLinksAccuracyGPTExperiment Setting=OVE...Experiment Setting=OVE-long2025.1088GPTExperiment Setting=RECExperiment Setting=REC2025.1086T5Experiment Setting=OVE...Experiment Setting=OVE-long2025.1076T5Experiment Setting=RECExperiment Setting=REC2025.1071