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

arXiv: https://arxiv.org/abs/2609.01794 · HTML: https://mlsanity.com/paper/2609.01794/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 58 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [What Artificial Neural Networks Can Tell Us About Human Language Acquisition](https://mlsanity.com/paper/2208.07998/) (2022)
- [Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs](https://mlsanity.com/paper/2403.19827/) (2024)
- [How Linguistics Learned to Stop Worrying and Love the Language Models](https://mlsanity.com/paper/2501.17047/) (2025)
- [Filtered Corpus Training (FiCT) Shows that Language Models can Generalize from Indirect Evidence](https://mlsanity.com/paper/2405.15750/) (2024)
- [Language Models Use Monotonicity to Assess NPI Licensing](https://mlsanity.com/paper/2105.13818/) (2021)
- [Both Direct and Indirect Evidence Contribute to Dative Alternation Preferences in Language Models](https://mlsanity.com/paper/2503.20850/) (2025)
- [BabyLM Turns 4 and Goes Multilingual: Call for Papers for the 2026 BabyLM Workshop](https://mlsanity.com/paper/2602.20092/) (2026)
- [Manipulating language models' training data to study syntactic constraint learning: the case of English passivization](https://mlsanity.com/paper/2407.04593/) (2024)
- [A systematic framework for generating novel experimental hypotheses from language models](https://mlsanity.com/paper/2408.05086/) (2024)
- [The Mechanistic Emergence of Symbol Grounding in Language Models](https://mlsanity.com/paper/2510.13796/) (2025)
- [UD-English-CHILDES: A Collected Resource of Gold and Silver Universal Dependencies Trees for Child Language Interactions](https://mlsanity.com/paper/2504.20304/) (2025)
- [CAIT: A Syntactic Parsing Toolkit for Child-Adult InTeractions](https://mlsanity.com/paper/2605.19718/) (2026)
- [Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs](https://mlsanity.com/paper/2605.23039/) (2026)

## Abstract (arXiv)

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.