ResearchBenchmarksClassification on Student random splits (test)Follow0.9Relative Error Rate ReductionOCTree0.4840.5920.70.808Jun 12, 2024Evaluation ResultsMethodMethodLinksRelative Error Rate ReductionTest Error RateOCTreeLLM Backbone=GPT-4oLLM Backbone=GPT-4o2024.060.9—CAAFELLM Backbone=GPT-4oLLM Backbone=GPT-4o2024.060.5—