[论文解读] The Reasoning Error About Reasoning: Why Different Types of Reasoning Require Different Representational Structures

Yiling Wu|arXiv (Cornell University)|Mar 23, 2026

Child and Animal Learning Development被引用 0

一句话总结

该论文提出一个四结构框架（可操作性、一致性、结构保持、组合性），不同的推理类型对其有不同的需求，并且主导边界将能够使用关联表示的推理与需要四个属性进行推理与形式逻辑的推理区分开来。

ABSTRACT

Different types of reasoning impose different structural demands on representational systems, yet no systematic account of these demands exists across psychology, AI, and philosophy of mind. I propose a framework identifying four structural properties of representational systems: operability, consistency, structural preservation, and compositionality. These properties are demanded to different degrees by different forms of reasoning, from induction through analogy and causal inference to deduction and formal logic. Each property excludes a distinct class of reasoning failure. The analysis reveals a principal structural boundary: reasoning types below it can operate on associative, probabilistic representations, while those above it require all four properties to be fully satisfied. Scaling statistical learning without structural reorganization is insufficient to cross this boundary, because the structural guarantees required by deductive reasoning cannot be approximated through probabilistic means. Converging evidence from AI evaluation, developmental psychology, and cognitive neuroscience supports the framework at different levels of directness. Three testable predictions are derived, including compounding degradation, selective vulnerability to targeted structural disruption, and irreducibility under scaling. The framework is a necessary-condition account, agnostic about representational format, that aims to reorganize existing debates rather than close them.

研究动机与目标

• 为推理类型如何映射到表征需求提供系统性解释的动机。
• 提出约束表征系统的四个结构性属性。
• 将五种推理类型（induction, analogy, causal inference, deduction, formal logic）映射到这些属性。
• 识别一个主导的结构性边界，并论证仅靠扩展统计学习无法跨越它。
• 概述可检验的预测并承认框架的局限性。

提出的方法

• 定义表征的四个结构属性及其必要性的论证。
• 分析五种推理类型，以确定对每种类型的最小、有益以及无关的结构性需求。
• 从结构性需求角度论证因果推理与演绎推理之间的主导边界。
• 提出一个实现无关、必要条件的解释框架，适用于不同表征格式。

实验结果

研究问题

• RQ1 为了支持不同推理类型，表征系统必须满足哪些结构属性？
• RQ2 在operability、consistency、structural preservation、compositionality方面，inductive、analogy、causal、deductive、formal logical 推理的需求有何差异？
• RQ3 在推理类型空间中是否存在一个主导边界，将能够在 probabilistic/associative 表征上操作的推理与需要完整四个属性的推理分开？
• RQ4 仅靠扩展统计学习而不进行结构重组，能跨越这一边界吗？

主要发现

• 不同推理类型对这些结构属性的需求程度不同：inductive 和 analogical 推理容忍部分或近似满足，而 deduction 需要四个属性的全部满足。
• deductive 推理需要可操作性、一致性、结构保持和组合性，无论是通过规则还是模型实现。
• 在因果推理与演绎推理之间存在一个主导的结构性边界，而演绎和形式逻辑推理需要完整的四个属性。
• 在不进行结构重组的前提下，扩展统计学习不足以跨越主导边界；要实现真正的演绎可靠性，必须满足结构属性。