ResearchBenchmarksClassification on Clinical random splits (test)Follow5.4Relative Error Rate ReductionOCTree1.762.7053.654.595Jun 12, 2024Evaluation ResultsMethodMethodLinksRelative Error Rate ReductionTest Error RateOCTreeLLM Backbone=GPT-4oLLM Backbone=GPT-4o2024.065.4—CAAFELLM Backbone=GPT-4oLLM Backbone=GPT-4o2024.061.9—