Disentangling Statistical Preemption from Entrenchment in Language Models' Avoidance of Overgeneralization

2026-09-01

AI Summary

研究通过控制语言模型训练实验，区分了预设和固化在避免过度泛化中的作用，发现模型主要依赖抽象预设而非具体动词层面的预设。

Abstract

How do learners avoid overgeneralizations such as Tom laughed me without explicit negative evidence? Constructionists have posited two proposals that describe indirect negative evidence against overgeneralizations: preemption (which privileges exposure to near-synonymous construction---e.g., she made him laugh) vs. entrenchment (all exposures to a verb's grammatical usages, including cases like He laughed). We disentangle these hypotheses by running controlled rearing experiments on LMs trained on child-caregiver conversations, where we systematically remove preemptive vs. non-preemptive evidence. We find that while LMs avoid overgeneralizations, they do not show preemption at a verb-specific level, instead showing weak but non-zero evidence of abstract preemption. Combined with results from analyzing the LMs' training dynamics, we find that LMs treat competing structures as indirect positive---as opposed to negative---evidence in the verb-specific condition. Insofar as preemption is the more plausible route to avoiding overgeneralizations in humans, our results point the need for there to be sensitivities to indirect negative evidence in neural network learners, and suggest new human experiments to test abstract preemption.

Problem

• overgeneralization
• preemption
• entrenchment

Innovation

• preemption
• entrenchment
• overgeneralization
• neural network learners
• indirect negative evidence