用验证引导生成精简推理链，提速降耗还更准。
ProofSketch: Efficient Verified Reasoning for Large Language Models
- 用符号闭包与词典验证，动态生成压缩推理草图
- 实验显示token消耗减少，准确率反而提升
- 适合需要高效可信推理的AI系统开发者
链式思维提示和自一致性等推理方法在多个推理任务中显著提升了大模型的准确性。然而这些方法生成冗长的推理链，导致令牌消耗、计算成本和延迟大幅增加。为解决这一效率问题，我们提出ProofSketch，一种基于验证引导的推理框架，融合符号闭包计算、词典验证和自适应草图生成。实验表明，ProofSketch持续降低令牌使用量的同时提升准确率，证明该方法为高效且可信赖推理提供了有前景的路径。
原文摘要 · Abstract (English)
Reasoning methods such as chain-of-thought prompting and self-consistency have shown immense potential to improve the accuracy of large language models across various reasoning tasks. However such methods involve generation of lengthy reasoning chains, which substantially increases token consumption, computational cost, and latency. To address this inefficiency, we propose ProofSketch, a verification-guided reasoning framework that integrates symbolic closure computation, lexicographic verification and adaptive sketch generation. Our experiments show that ProofSketch consistently reduces token usage while improving accuracy, demonstrating that this approach offers a promising path for efficient and trustworthy reasoning.
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。