TensorX
返回文献探索

Paper · arXiv 2502.18600

Chain of Draft: Thinking Faster by Writing Less

Silei Xu, Wenhao Xie, Lingxiao Zhao, Pengcheng He

50 upvotesFebruary 25, 2025arXiv 预印本
AI 摘要

Chain of Draft (CoD) improves the efficiency of Large Language Models (LLMs) in reasoning tasks by generating concise intermediate thoughts, enhancing accuracy while reducing token usage, cost, and latency.

Chain-of-Thought (CoT)Chain of Draft (CoD)Large Language Models (LLMs)reasoning tasksintermediate reasoning outputscritical insights

Abstract

Large Language Models (LLMs) have demonstrated remarkable performance in solving complex reasoning tasks through mechanisms like Chain-of-Thought (CoT) prompting, which emphasizes verbose, step-by-step reasoning. However, humans typically employ a more efficient strategy: drafting concise intermediate thoughts that capture only essential information. In this work, we propose Chain of Draft (CoD), a novel paradigm inspired by human cognitive processes, where LLMs generate minimalistic yet informative intermediate reasoning outputs while solving tasks. By reducing verbosity and focusing on critical insights, CoD matches or surpasses CoT in accuracy while using as little as only 7.6% of the tokens, significantly reducing cost and latency across various reasoning tasks.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
Chain of Draft: Thinking Faster by Writing Less | TensorX