压缩思维链：通过稠密表示实现高效推理
Compressed Chain of Thought: Efficient Reasoning Through Dense Representations
AI总结：
本文提出压缩思维链（CCoT）框架，通过生成可变长度的连续沉思标记作为显式推理链的压缩表示，在现成解码器语言模型上实现高效推理，并可通过控制标记数量自适应调整推理改进。
摘要：
思维链（Chain-of-Thought, CoT）解码使语言模型能够提升推理性能，但代价是解码过程中的高生成延迟。近期研究探索了沉思标记（contemplation tokens）的变体，该术语由我们提出，指在推理期间用于允许额外计算的特殊标记。先前的工作考虑使用从离散嵌入集合中抽取的固定长度序列作为沉思标记。在此，我们提出压缩思维链（Compressed Chain-of-Thought, CCoT），一个生成可变序列长度的有内容且连续的沉思标记的框架。生成的沉思标记是显式推理链的压缩表示，我们的方法可应用于现成的解码器语言模型。通过实验，我们展示了CCoT如何能够在稠密的有内容表示上进行额外推理，从而实现相应的准确性提升。此外，推理改进可通过控制生成的沉思标记数量按需自适应调整。
英文摘要：
Chain-of-thought (CoT) decoding enables language models to improve reasoning performance at the cost of high generation latency in decoding. Recent proposals have explored variants of contemplation tokens, a term we introduce that refers to special tokens used during inference to allow for extra computation. Prior work has considered fixed-length sequences drawn from a discrete set of embeddings as contemplation tokens. Here we propose Compressed Chain-of-Thought (CCoT), a framework to generate contentful and continuous contemplation tokens of variable sequence length. The generated contemplation tokens are compressed representations of explicit reasoning chains, and our method can be applied to off-the-shelf decoder language models. Through experiments, we illustrate how CCoT enables additional reasoning over dense contentful representations to achieve corresponding improvements in accuracy. Moreover, the reasoning improvements can be adaptively modified on demand by controlling the number of contemplation tokens generated.
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。
