Stepwise inference protocols, such as scratchpads and chain-of-thought, help
language models solve complex problems by decomposing them into a sequence of
simpler subproblems. Despite the significant gain in performance achieved via
these protocols, the underlying mechanisms of stepwise inference have remained
elusive. To address this, we propose to study autoregressive Transformer models
on a synthetic task that embodies the multi-step nature of problems where
stepwise inference is generally most useful. Specifically, we define a graph
navigation problem wherein a model is tasked with traversing a path from a
start to a goal node on the graph. Despite is simplicity, we find we can
empirically reproduce and analyze several phenomena observed at scale: (i) the
stepwise inference reasoning gap, the cause of which we find in the structure
of the training data; (ii) a diversity-accuracy tradeoff in model generations
as sampling temperature varies; (iii) a simplicity bias in the model's output;
and (iv) compositional generalization and a primacy bias with in-context
exemplars. Overall, our work introduces a grounded, synthetic framework for
studying stepwise inference and offers mechanistic hypotheses that can lay the
foundation for a deeper understanding of this phenomenon.

通过研究一种合成任务中的自回归 Transformer 模型，我们揭示了逐步推理的机制，并发现了在该任务中观察到的几个现象：（i）逐步推理推理间隔；（ii）模型生成中多样性与准确性之间的权衡；（iii）模型输出的简洁偏见；以及（iv）上下文示例中的组合概括和原位偏见。这项工作引入了一个基于合成框架的研究逐步推理，并提供了可奠定对该现象更深入理解基础的机制性假设。