arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.01992cs.AI
收藏

Transformer中的涌现类比推理

Emergent Analogical Reasoning in Transformers

The University of Tokyo(东京大学);Google Deep Mind(谷歌深Mind)

Gouki Minegishi, Jingyuan Feng, Hiroki Furuta, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

AI总结:

本研究通过范畴论中的函子概念形式化类比推理,设计合成任务探究Transformer中类比推理的涌现机制,发现其依赖于数据特征、优化选择和模型规模,并通过机制分析揭示几何对齐和函子应用两个关键组件。

摘要:

类比是人类智能的核心能力,使得在一个领域中发现的抽象模式能够应用于另一个领域。尽管类比在认知中占据核心地位,但Transformer获取并实现类比推理的机制仍知之甚少。受范畴论中函子概念的启发,我们将类比推理形式化为跨类别实体间对应关系的推断。基于这一表述,我们引入了在受控设置下评估类比推理涌现的合成任务。我们发现,类比推理的涌现对数据特征、优化选择和模型规模高度敏感。通过机制分析,我们展示了Transformer中的类比推理分解为两个关键组件:(1) 嵌入空间中关系结构的几何对齐,以及(2) Transformer内部函子的应用。这些机制使模型能够将关系结构从一个类别转移到另一个类别,从而实现类比。最后,我们量化了这些效应,并在预训练的大型语言模型中观察到了相同的趋势。通过这样做,我们将类比从一个抽象的认知概念转变为现代神经网络中一个具体的、基于机制的現象。

英文摘要:

Analogy is a central faculty of human intelligence, enabling abstract patterns discovered in one domain to be applied to another. Despite its central role in cognition, the mechanisms by which Transformers acquire and implement analogical reasoning remain poorly understood. In this work, inspired by the notion of functors in category theory, we formalize analogical reasoning as the inference of correspondences between entities across categories. Based on this formulation, we introduce synthetic tasks that evaluate the emergence of analogical reasoning under controlled settings. We find that the emergence of analogical reasoning is highly sensitive to data characteristics, optimization choices, and model scale. Through mechanistic analysis, we show that analogical reasoning in Transformers decomposes into two key components: (1) geometric alignment of relational structure in the embedding space, and (2) the application of a functor within the Transformer. These mechanisms enable models to transfer relational structure from one category to another, realizing analogy. Finally, we quantify these effects and find that the same trends are observed in pretrained LLMs. In doing so, we move analogy from an abstract cognitive notion to a concrete, mechanistically grounded phenomenon in modern neural networks.

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。

↑