用思维草图减少大模型推理的冗余，省 token 还更准。
Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching
- 用认知启发的三种思路动态选推理方式，自适应压缩输出。
- 在18个数据集上最多节省84%令牌，数学等任务还更准。
- 适合追求高效推理的场景，尤其适合资源受限部署。
大语言模型通过思维链（Chain-of-Thought, CoT）提示实现强推理能力，但中间输出常过于冗长，带来高计算开销。我们提出思维草图（Sketch-of-Thought, SoT）框架，融合认知启发式推理范式与语言约束，在保持推理准确率的同时减少令牌使用。SoT为灵活模块化设计，包含概念链、分块符号和专家词典三种范式，由轻量路由模型在测试时动态选择。在覆盖多个领域、语言和模态的18个推理数据集上，SoT实现最高达84%的令牌减少，且在数学和多跳推理等任务中甚至提升准确率。
原文摘要 · Abstract (English)
Recent advances in large language models (LLMs) have enabled strong reasoning capabilities through Chain-of-Thought (CoT) prompting, which elicits step-by-step problem solving, but often at the cost of excessive verbosity in intermediate outputs, leading to increased computational overhead. We propose Sketch-of-Thought (SoT), a prompting framework that integrates cognitively inspired reasoning paradigms with linguistic constraints to reduce token usage while preserving reasoning accuracy. SoT is designed as a flexible, modular approach and is instantiated with three paradigms--Conceptual Chaining, Chunked Symbolism, and Expert Lexicons--each tailored to distinct reasoning tasks and selected dynamically at test-time by a lightweight routing model. Across 18 reasoning datasets spanning multiple domains, languages, and modalities, SoT achieves token reductions of up to 84% with minimal accuracy loss. In tasks such as mathematical and multi-hop reasoning, it even improves accuracy while shortening outputs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。