Large language models (LLMs) have achieved widespread success on a variety of in-context few-shot tasks, but this success is typically evaluated via correctness rather than consistency. We argue that self-consistency is an important criteria for valid multi-step reasoning in tasks where the solution is composed of the answers to multiple sub-steps. We propose two types of self-consistency that are particularly important for multi-step reasoning -- hypothetical consistency (a model's ability to predict what its output would be in a hypothetical other context) and compositional consistency (consistency of a model's final outputs when intermediate sub-steps are replaced with the model's outputs for those steps). We demonstrate that multiple variants of the GPT-3/-4 models exhibit poor consistency rates across both types of consistency on a variety of tasks.

翻译：大语言模型（LLMs）在多种上下文少样本任务中取得了广泛成功，但这种成功通常基于正确性而非一致性进行评估。我们提出，在解由多个子步骤答案组成的任务中，自我一致性是多步推理有效性的重要标准。我们提出两种对多步推理尤为重要的自我一致性——假设一致性（模型预测其在假设的其他上下文中的输出的能力）和组合一致性（当中间子步骤被替换为模型对这些步骤的输出时，模型最终输出的一致性）。我们在多种任务上证明，GPT-3/-4系列的不同变体在这两类一致性上均表现出较低的一致性率。