对比式思维链提示

摘要

尽管思维链在增强语言模型推理方面取得了成功，但其基本过程仍不太清楚。虽然逻辑上合理的推理在思维链中显然至关重要，但先前的研究惊人地发现，使用无效演示时影响甚微。此外，传统的思维链未告知语言模型应避免哪些错误，这可能导致更多错误。因此，受人类如何从正面和负面示例中学习的启发，我们提出对比思维链以增强语言模型推理能力。与传统思维链相比，我们的方法提供有效和无效推理演示，引导模型逐步推理并减少推理错误。为了提高泛化能力，我们引入了一种自动构建对比演示的方法。我们在推理基准上的实验表明，对比思维链可以作为思维链提示的一种通用增强方法。

English

Despite the success of chain of thought in enhancing language model reasoning, the underlying process remains less well understood. Although logically sound reasoning appears inherently crucial for chain of thought, prior studies surprisingly reveal minimal impact when using invalid demonstrations instead. Furthermore, the conventional chain of thought does not inform language models on what mistakes to avoid, which potentially leads to more errors. Hence, inspired by how humans can learn from both positive and negative examples, we propose contrastive chain of thought to enhance language model reasoning. Compared to the conventional chain of thought, our approach provides both valid and invalid reasoning demonstrations, to guide the model to reason step-by-step while reducing reasoning mistakes. To improve generalization, we introduce an automatic method to construct contrastive demonstrations. Our experiments on reasoning benchmarks demonstrate that contrastive chain of thought can serve as a general enhancement of chain-of-thought prompting.

对比式思维链提示

Contrastive Chain-of-Thought Prompting

摘要

Support