🧠#ChainofDraft is inspired by human problem-solving - using concise drafts instead of verbose reasoning
📈 Matches or exceeds #ChainofThought accuracy across multiple reasoning tasks
âš¡ Reduces token usage by up to 92.4% compared to verbose methods
📈 Matches or exceeds #ChainofThought accuracy across multiple reasoning tasks
âš¡ Reduces token usage by up to 92.4% compared to verbose methods
Comments
🔄 Works with leading #LLMs like GPT-4o and Claude 3.5 Sonnet
🧮 Excels in arithmetic, common-sense, and symbolic reasoning benchmarks
https://arxiv.org/abs/2502.18600