entrenchment

Tag

Cards List
#entrenchment

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

arXiv cs.CL · 2026-09-03 Cached

This paper disentangles statistical preemption from entrenchment in language models' avoidance of overgeneralizations through controlled experiments, finding that LMs exhibit abstract preemption rather than verb-specific preemption, with implications for human language learning.

0 favorites 0 likes
#entrenchment

Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt

arXiv cs.CL · 2026-06-03 Cached

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.

0 favorites 0 likes
← Back to home

Submit Feedback