Tag
This paper investigates whether Large Language Models exhibit the same usage-based linguistic productivity constraints (entrenchment and preemption) as humans, finding that models can reproduce coercion but fail to apply statistical preemption to avoid overgeneralization.
This paper provides causal evidence that large language models acquire negative linguistic knowledge (what not to say) through statistical preemption, a mechanism from Construction Grammar, by showing that manipulating competing-form frequencies via fine-tuning shifts preemption behavior in predicted directions.