无需提示的思维链推理
Chain-of-Thought Reasoning Without Prompting
AI总结：
本研究提出通过改变解码过程而非提示来激发LLMs的思维链推理，发现前k备选token中常含思维链路径，且置信度可区分思维链，实验证明该方法有效。
摘要：
在提升大型语言模型（LLMs）的推理能力方面，以往的研究主要集中于特定的提示技术，如少样本或零样本思维链（CoT）提示。这些方法虽然有效，但往往涉及大量人工提示工程。我们的研究采用了一种新颖的方法，提出问题：LLMs能否在无需提示的情况下有效推理？我们的发现揭示了一个有趣的现象：通过简单地改变解码过程，就可以从预训练的LLMs中引出思维链推理路径。我们不是采用传统的贪婪解码，而是研究前k个备选token，发现思维链路径常常内在于这些序列中。这种方法不仅绕过了提示的混淆因素，还使我们能够评估LLMs的内在推理能力。此外，我们观察到解码路径中思维链的存在与模型解码答案的更高置信度相关。这种置信度指标能有效区分思维链与非思维链路径。在各种推理基准上的广泛实证研究表明，所提出的思维链解码能有效激发语言模型的推理能力，而这些能力此前被标准贪婪解码所掩盖。
英文摘要：
In enhancing the reasoning capabilities of large language models (LLMs), prior research primarily focuses on specific prompting techniques such as few-shot or zero-shot chain-of-thought (CoT) prompting. These methods, while effective, often involve manually intensive prompt engineering. Our study takes a novel approach by asking: Can LLMs reason effectively without prompting? Our findings reveal that, intriguingly, CoT reasoning paths can be elicited from pre-trained LLMs by simply altering the \textit{decoding} process. Rather than conventional greedy decoding, we investigate the top-$k$ alternative tokens, uncovering that CoT paths are frequently inherent in these sequences. This approach not only bypasses the confounders of prompting but also allows us to assess the LLMs' \textit{intrinsic} reasoning abilities. Moreover, we observe that the presence of a CoT in the decoding path correlates with a higher confidence in the model's decoded answer. This confidence metric effectively differentiates between CoT and non-CoT paths. Extensive empirical studies on various reasoning benchmarks show that the proposed CoT-decoding effectively elicits reasoning capabilities from language models, which were previously obscured by standard greedy decoding.
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。
