推理路径作为输入仍然有效吗？将后推理与思维链压缩连接起来
Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression
AI总结：
提出后推理范式，通过将思维链作为上下文输入来简化推理任务，并设计UCoT框架训练轻量级压缩器生成软令牌形式的上下文思维链，从而在保持推理能力的同时显著压缩输出长度。
摘要：
近期发展使得大型语言模型（LLMs）能够通过长思维链（CoT）实现高级推理，但这是以牺牲推理效率为代价来换取性能。现有工作侧重于压缩推理过程中生成的CoT，但这会损害推导正确答案所需的信息。在这项工作中，我们提出后推理（post-reasoning）这一推理范式，将CoT作为上下文的一部分，以简化LLMs的推理任务。我们发现后推理显著减少了LLMs的生成长度，但其有效性取决于上下文CoT生成的效率和可靠性。因此，我们提出UCoT（Upfront CoT），一个用于CoT压缩的高效后推理框架。UCoT训练一个轻量级模型（压缩器）以软令牌形式提供上下文CoT，并训练LLM（执行器）利用此上下文CoT生成最终答案。大量实验表明，UCoT在保持执行器强大推理能力的同时，显著减少了CoT的长度。值得一提的是，当将UCoT应用于Qwen2.5-7B-Instruct模型时，在GSM8K数据集上的令牌使用量减少了50%，而性能比最先进（SOTA）方法高出3.08%。
英文摘要：
Recent developments have enabled advanced reasoning in Large Language Models (LLMs) via long Chain-of-Thought (CoT), trading efficiency during inference for performance. Existing works focus on compressing generated CoT in reasoning, which impairs the necessary information for deriving the correct answer. In this work, we propose post-reasoning, a reasoning paradigm that takes CoT as a part of context to simplify the reasoning task for LLMs. We find that post-reasoning significantly reduces the generation length of LLMs, but its effectiveness hinges on the efficiency and the reliability of the contextual CoT generation. Therefore, we propose Upfront CoT (UCoT), an efficient post-reasoning framework for CoT compression. UCoT trains a lightweight model (compressor) to provide contextual CoT in form of soft tokens and trains the LLM (executor) to leverage this contextual CoT for producing the final answer. Extensive experiments show that UCoT maintains the powerful reasoning ability of executor while significantly reducing the length of CoT. It is worth mentioning that when applying UCoT to the Qwen2.5-7B-Instruct model, the usage of tokens on GSM8K dataset is reduced by 50%, while the performance is 3.08% higher than that of the state-of-the-art (SOTA) method.
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。
