Abstract reasoning, the ability to reason from the abstract essence of a problem, serves as a key to generalization in human reasoning. However, eliciting language models to perform reasoning with abstraction remains unexplored. This paper seeks to bridge this gap by introducing a novel structured reasoning format called Abstraction-of-Thought (AoT). The uniqueness of AoT lies in its explicit requirement for varying levels of abstraction within the reasoning process. This approach could elicit language models to first contemplate on the abstract level before incorporating concrete details, which is overlooked by the prevailing step-by-step Chain-of-Thought (CoT) method. To align models with the AoT format, we present AoT Collection, a generic finetuning dataset consisting of 348k high-quality samples with AoT reasoning processes, collected via an automated and scalable pipeline. We finetune a wide range of language models with AoT Collection and conduct extensive evaluations on 23 unseen tasks from the challenging benchmark Big-Bench Hard. Experimental results indicate that models aligned to AoT reasoning format substantially outperform those aligned to CoT in many reasoning tasks.

翻译：抽象推理——从问题的抽象本质进行推理的能力——是人类推理中泛化的关键。然而，如何激发语言模型进行抽象推理仍未被探索。本文旨在通过引入一种名为思维抽象化的新型结构化推理格式来弥合这一差距。AoT的独特性在于其明确要求在推理过程中包含不同层次的抽象。这种方法可以激发语言模型在融入具体细节之前先进行抽象层面的思考，而这是当前主流的逐步思维链方法所忽视的。为了使模型与AoT格式对齐，我们提出了AoT Collection，这是一个包含34.8万个高质量样本（附带AoT推理过程）的通用微调数据集，通过自动化且可扩展的流程收集而成。我们使用AoT Collection对多种语言模型进行微调，并在具有挑战性的基准测试Big-Bench Hard中的23个未见任务上进行了广泛评估。实验结果表明，采用AoT推理格式对齐的模型在多项推理任务中显著优于采用CoT格式对齐的模型。