用不确定性选择最优推理示范，让大模型零样本推理更准。
Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection
- 基于模型不确定度自动筛选有效推理示范，无需参数访问。
- 在四个复杂推理基准上均优于现有方法，表现稳定可靠。
- 适合需要高效零样本推理的科研与工程场景。
思维链（CoT）提示通过结构化推理过程显著提升了大语言模型的能力。然而，现有方法存在明显局限：手工设计的示范需要大量人工经验，而触发词则易产生误判。本文提出零样本不确定性选择（ZEUS）方法，利用不确定性估计来选择有效的示范，无需访问模型参数。与传统方法相比，ZEUS能高灵敏度区分有效与无效问题，确保选择更精确可靠。大规模评估显示，ZEUS在四个具有挑战性的推理基准上持续优于现有CoT策略，展现出优异的鲁棒性与可扩展性。
原文摘要 · Abstract (English)
Chain-of-thought (CoT) prompting has significantly enhanced the capability of large language models (LLMs) by structuring their reasoning processes. However, existing methods face critical limitations: handcrafted demonstrations require extensive human expertise, while trigger phrases are prone to inaccuracies. In this paper, we propose the Zero-shot Uncertainty-based Selection (ZEUS) method, a novel approach that improves CoT prompting by utilizing uncertainty estimates to select effective demonstrations without needing access to model parameters. Unlike traditional methods, ZEUS offers high sensitivity in distinguishing between helpful and ineffective questions, ensuring more precise and reliable selection. Our extensive evaluation shows that ZEUS consistently outperforms existing CoT strategies across four challenging reasoning benchmarks, demonstrating its robustness and scalability.
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。