思维抽象使语言模型成为更好的推理器
Abstraction-of-Thought Makes Language Models Better Reasoners
AI总结：
本文提出新型结构化推理格式思维抽象（AoT），通过构建包含348k样本的微调数据集AoT Collection，引导语言模型在推理中先进行抽象思考再融入具体细节，在Big-Bench Hard基准上显著优于传统思维链方法。
摘要：
抽象推理，即从问题的抽象本质出发进行推理的能力，是人类推理中实现泛化的关键。然而，引导语言模型进行抽象推理仍未被探索。本文通过引入一种名为思维抽象（AoT）的新型结构化推理格式来弥补这一空白。AoT的独特性在于它明确要求在推理过程中进行不同层次的抽象。这种方法能够引导语言模型在融入具体细节之前先在抽象层面上进行思考，而这是目前流行的逐步思维链（CoT）方法所忽视的。为了使模型与AoT格式对齐，我们提出了AoT Collection，这是一个通用的微调数据集，包含348k个带有AoT推理过程的高质量样本，这些样本是通过自动化且可扩展的流程收集的。我们使用AoT Collection对各种语言模型进行微调，并在具有挑战性的基准Big-Bench Hard的23个未见任务上进行了广泛评估。实验结果表明，与CoT对齐的模型相比，与AoT推理格式对齐的模型在许多推理任务中表现显著更优。
英文摘要：
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.
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。
