Paper

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

Unreadunread

AI summary

arXiv:2606. 02953v1 Announce Type: new Abstract: Usage-based theories of grammars posit that creative productivity of the structures of language is both bolstered and constrained by two distinct frequency signals: entrenchment, stemming from high frequency usage, and preemption, stemming from having never observed a particular linguistic structure in a context where one might expect that structure to appear.

Reading status

Priority

About this paper

Authors: Claire Bonial, Claire Benet Post, Laura Michaelis, Harish Tayyar Madabushi
Released: 2026-06-03 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, word, rate, does, trained, test, language, model. Source: arxiv cs.CL (NLP).
arXiv: 2606.02953

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.