通过不确定性引导的策略选择增强零样本思维链提示
Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection
AI总结：
针对零样本 CoT 提示中人工示例成本高、触发短语不可靠的问题，提出 ZEUS，利用不确定性估计选择有效示例，并在四个推理基准上持续优于现有策略。
摘要：
思维链（CoT）提示通过构建大语言模型（LLM）的推理过程，显著增强了其能力。然而，现有方法面临关键局限：手工制作的示例需要大量人类专业知识，而触发短语容易出现不准确。本文提出零样本基于不确定性的选择（ZEUS）方法，这是一种新颖途径，通过利用不确定性估计选择有效示例来改进 CoT 提示，且无需访问模型参数。与传统方法不同，ZEUS 在区分有帮助和无效问题方面具有高敏感性，可确保更精确、可靠的选择。大量评估表明，ZEUS 在四个具有挑战性的推理基准上持续优于现有 CoT 策略，证明了其鲁棒性和可扩展性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
