C3oT: 生成更短的思维链而不损害有效性
C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness
AI总结：
针对思维链过长导致解码成本高的问题，提出C3oT框架，通过压缩器、条件训练和条件推理，在保持有效性的同时将CoT长度压缩50%以上。
摘要：
在推导答案之前生成思维链（Chain-of-Thought, CoT）可以有效提升大型语言模型（LLMs）的推理能力，并显著提高生成答案的准确性。然而，在大多数情况下，生成的CoT长度远长于期望的最终答案，这导致了额外的解码成本。此外，现有研究发现，即使保留关键信息，缩短CoT中的推理步骤也会削弱LLMs的能力。这些现象使得LLMs和CoT在许多仅需要最终答案且对延迟敏感的真实世界应用中难以使用，例如搜索和推荐。为了降低模型解码成本并缩短生成的CoT长度，本文提出了条件压缩思维链（Conditioned Compressed Chain-of-Thought, C3oT），这是一个CoT压缩框架，包含一个压缩器，用于将原始的较长CoT压缩为较短的CoT，同时保留关键信息和可解释性；一个条件训练方法，用于同时使用较长CoT和较短CoT训练LLMs，以学习它们之间的对应关系；以及一个条件推理方法，通过生成较短CoT来获得从较长CoT中学到的推理能力。我们在来自算术和常识场景的四个数据集上进行了实验，结果表明所提出的方法能够将生成的CoT长度压缩多达50%以上，而不损害其有效性。
英文摘要：
Generating Chain-of-Thought (CoT) before deriving the answer can effectively improve the reasoning capabilities of large language models (LLMs) and significantly improve the accuracy of the generated answer. However, in most cases, the length of the generated CoT is much longer than the desired final answer, which results in additional decoding costs. Furthermore, existing research has discovered that shortening the reasoning steps in CoT, even while preserving the key information, diminishes LLMs' abilities. These phenomena make it difficult to use LLMs and CoT in many real-world applications that only require the final answer and are sensitive to latency, such as search and recommendation. To reduce the costs of model decoding and shorten the length of the generated CoT, this paper presents $\textbf{C}$onditioned $\textbf{C}$ompressed $\textbf{C}$hain-of-$\textbf{T}$hought (C3oT), a CoT compression framework that involves a compressor to compress an original longer CoT into a shorter CoT while maintaining key information and interpretability, a conditioned training method to train LLMs with both longer CoT and shorter CoT simultaneously to learn the corresponding relationships between them, and a conditioned inference method to gain the reasoning ability learned from longer CoT by generating shorter CoT. We conduct experiments over four datasets from arithmetic and commonsense scenarios, showing that the proposed method is capable of compressing the length of generated CoT by up to more than 50% without compromising its effectiveness.
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。
