潜在思维链？解码深度循环 Transformer
Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer
AI总结：
本文借助 Logit Lens 与 Coda Lens 探测 Huginn-3.5B 的算术推理过程，发现其缺乏清晰可解释的潜在 CoT，增加循环深度也仅有边际收益。
摘要：
思维链（CoT）推理已使基于 Transformer 的语言模型在复杂数学和多步规划方面表现出色。然而，在标准的仅解码器架构中，这些推理步骤以自然语言外化，虽提升了可解释性，却以效率为代价。为捕捉难以用语言表示的推理，许多研究探索了循环架构，旨在将推理内化到潜在空间中，从而可能支持潜在 CoT。本文研究此类推理结构是否会在 Huginn-3.5B 中涌现；这是一种深度循环 Transformer，在推理时复用层而不增加参数量。我们使用包括 Logit Lens 和 Coda Lens 在内的一组探测技术，考察该模型在算术任务上的内部行为。研究结果通过追踪最终结果 token 和中间结果 token 的排名轨迹，揭示出可解释潜在 CoT 的证据有限。此外，我们发现各循环块之间存在显著的探测不一致性，隐藏状态的可解释性在很大程度上同时取决于层索引和解码方法。最后，我们通过实验表明，增加循环深度只会带来边际收益，且远不及显式外化推理步骤的模型。代码可在 https://github.com/wenquanlu/huginn-latent-cot 获取。
英文摘要：
Chain-of-thought (CoT) reasoning has enabled transformer-based language models to excel at complex mathematics and multi-step planning. However, in standard decoder-only architectures, these reasoning steps are externalized in natural language, improving interpretability at the cost of efficiency. To capture reasoning that is not easily represented in words, many works have explored recurrent architectures that aim to internalize reasoning in latent space, potentially supporting latent CoT. In this paper, we investigate whether such reasoning structures emerge in Huginn-3.5B, a depth-recurrent Transformer that reuses layers at inference time without increasing parameter count. We examine the model's internal behavior on arithmetic tasks using a suite of probing techniques including the Logit Lens and Coda Lens. Our findings reveal limited evidence of interpretable latent CoT by tracking rank trajectories of final and intermediate result tokens. Furthermore, we uncover significant probing inconsistencies across recurrent blocks, where the interpretability of hidden states depends heavily on both the layer index and the decoding method. Finally, we empirically show that increasing recurrence depth yields only marginal gains and falls well short of models that explicitly externalize reasoning steps. The code is available at https://github.com/wenquanlu/huginn-latent-cot.
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。
