理解 Chain-of-Thought 推理中的隐藏计算
Understanding Hidden Computations in Chain-of-Thought Reasoning
AI总结：
针对填充字符替代 CoT 后模型仍可推理的现象，本文利用 logit lens 与 token 排名分析逐层表示，实现隐藏推理字符的无损恢复。
摘要：
Chain-of-Thought（CoT）提示显著增强了大型语言模型的推理能力。然而，近期研究表明，即使 CoT 被替换为填充（隐藏）字符（例如“...”），模型仍能执行复杂推理任务，这留下了模型如何在内部处理和表示推理步骤的开放问题。本文研究了解码使用填充 CoT 序列训练的 transformer 模型中这些隐藏字符的方法。通过使用 logit lens 方法分析逐层表示并检查 token 排名，我们证明隐藏字符可以在不损失性能的情况下被恢复。我们的发现为理解 transformer 模型的内部机制提供了洞见，并为提升语言模型推理的可解释性和透明度开辟了途径。
英文摘要：
Chain-of-Thought (CoT) prompting has significantly enhanced the reasoning abilities of large language models. However, recent studies have shown that models can still perform complex reasoning tasks even when the CoT is replaced with filler(hidden) characters (e.g., "..."), leaving open questions about how models internally process and represent reasoning steps. In this paper, we investigate methods to decode these hidden characters in transformer models trained with filler CoT sequences. By analyzing layer-wise representations using the logit lens method and examining token rankings, we demonstrate that the hidden characters can be recovered without loss of performance. Our findings provide insights into the internal mechanisms of transformer models and open avenues for improving interpretability and transparency in language model reasoning.
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。
