对比思维链提示
Contrastive Chain-of-Thought Prompting
AI总结：
提出对比思维链，通过同时提供有效和无效推理演示并自动构建，增强语言模型推理并减少错误，在推理基准上验证其作为通用增强手段的有效性。
摘要：
尽管思维链在增强语言模型推理能力方面取得了成功，但其底层过程仍未被充分理解。虽然逻辑上合理的推理似乎对思维链至关重要，但先前的研究令人惊讶地发现，使用无效演示时影响甚微。此外，传统的思维链并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，受人类能从正面和负面例子中学习的启发，我们提出了对比思维链以增强语言模型推理。与传统思维链相比，我们的方法提供有效和无效的推理演示，引导模型逐步推理同时减少推理错误。为提高泛化能力，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通用增强手段。
英文摘要：
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.
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。
