Sign up to save your podcasts
Or
Share Chain of Draft: Thinking Faster by Writing Less
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Chain of Draft: Thinking Faster by Writing Less
🤗 Upvotes: 27 | cs.CL, I.2.7
Authors:
Silei Xu, Wenhao Xie, Lingxiao Zhao, Pengcheng He
Title:
Chain of Draft: Thinking Faster by Writing Less
Arxiv:
http://arxiv.org/abs/2502.18600v1
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.
View all episodes
By Jingwen Liang, Gengyu Wang🤗 Upvotes: 27 | cs.CL, I.2.7
Authors:
Silei Xu, Wenhao Xie, Lingxiao Zhao, Pengcheng He
Title:
Chain of Draft: Thinking Faster by Writing Less
Arxiv:
http://arxiv.org/abs/2502.18600v1
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.