Cognitive Thermometers: Machine Learning and Logical Complexity

Computer Science > Computation and Language arXiv:2610.10724 (cs) [Submitted on 7 Oct 2026] Title: Cognitive Thermometers: Machine Learning and Logical Complexity Authors: Shane Steinert-Threlkeld, Jakub Szymanik.

计算机科学 > 计算与语言 arXiv:2610.10724 (cs) [提交于 2026 年 10 月 7 日] 标题：认知温度计：机器学习与逻辑复杂性 作者：Shane Steinert-Threlkeld, Jakub Szymanik。

Abstract: How does the human mind represent semantic categories? Why do natural languages favor certain meanings over others? Prior explanations have relied on logical definability and complexity, but these are highly sensitive to the choice of logical language, rendering some design choices unmotivated.

摘要：人类思维如何表征语义范畴？为什么自然语言偏好某些意义而非其他？先前的解释依赖于逻辑可定义性和复杂性，但这些解释对逻辑语言的选择高度敏感，导致一些设计选择缺乏动机。

In this article, we propose that machine learning provides a somewhat more agnostic approach to measuring semantic complexity. We review emerging evidence that logic and machine learning often yield converging results on relative complexity and its resulting effects in semantic typology.

在本文中，我们提出机器学习为衡量语义复杂性提供了一种更为不可知论的方法。我们回顾了新兴证据，这些证据表明逻辑和机器学习在相对复杂性及其在语义类型学中的结果影响方面往往得出趋同的结果。

Where they diverge, learning appears to be a better explanation than logical complexity. We argue that treating machine learning models as “cognitive thermometers” enables a unified approach to complexity that bridges symbolic logic and connectionist AI.

在它们产生分歧的地方，学习似乎比逻辑复杂性提供了更好的解释。我们认为，将机器学习模型视为“认知温度计”能够实现一种统一的复杂性方法，从而架起符号逻辑与联结主义人工智能之间的桥梁。