ResearchBenchmarksConclusion Generation on Crafted Rules Dataset (test)Follow0.739BLEUEngine0.321960.430230.53850.64677Feb 18, 2024Evaluation ResultsMethodMethodLinksBLEUEnginebackbone=Mistral-7b, m...backbone=Mistral-7b, mode=fine-tuned2024.020.739GPT-4mode=promptingmode=prompting2024.020.414GPT-3.5mode=promptingmode=prompting2024.020.338