通过推理模式增强大型语言模型中的思维链提示
Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns
AI总结：
本文提出利用推理模式选择多样化示例以增强思维链提示，减轻噪声影响并提供可解释性，实验证明该方法在多种推理任务上更稳健且持续改进。
摘要：
思维链（Chain of Thought, CoT）提示可以鼓励语言模型进行多步逻辑推理。所提供的示例质量显著影响下游推理任务的成功。当前无监督的CoT方法主要基于问题的语义选择示例，这可能会引入噪声并缺乏可解释性。在本文中，我们提出利用推理模式来增强CoT提示的有效性。推理模式表示语言模型得出最终结果的过程。通过利用先验知识和基于大型模型的提示方法，我们首先构建特定于任务的模式集。然后，我们基于不同的推理模式选择多样化的示例。这种方法不仅减轻了噪声的影响，还提供了明确的可解释性，以帮助我们理解CoT的机制。大量实验表明，我们的方法更加稳健，并在各种推理任务中持续带来改进。
英文摘要：
Chain of Thought (CoT) prompting can encourage language models to engage in multi-step logical reasoning. The quality of the provided demonstrations significantly influences the success of downstream inference tasks. Current unsupervised CoT methods primarily select examples based on the semantics of the questions, which can introduce noise and lack interpretability. In this paper, we propose leveraging reasoning patterns to enhance CoT prompting effectiveness. Reasoning patterns represent the process by which language models arrive at their final results. By utilizing prior knowledge and prompt-based methods from large models, we first construct task-specific pattern sets. We then select diverse demonstrations based on different reasoning patterns. This approach not only mitigates the impact of noise but also provides explicit interpretability to help us understand the mechanisms of CoT. Extensive experiments demonstrate that our method is more robust and consistently leads to improvements across various reasoning tasks.
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。
