Metraipolis › archive › dc_ca893b1dcba9

Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation — arXiv:2609.04484

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04484
License (as archived)
CC0-1.0
Archived
2026-10-16T22:26:21.335Z
SHA-256 of the archived text
8e8b46e6a53414fea4229e9f3eecbe0c323c1c2c36bc95a8695a67f9f86520e9
Stable URL of this page
https://metraipolis.com/documento/dc_ca893b1dcba9

How to cite

Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation — arXiv:2609.04484 — arXiv (en), https://arxiv.org/abs/2609.04484 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca893b1dcba9 (Metraipolis archive dc_ca893b1dcba9, sha256 8e8b46e6a53414fea4229e9f3eecbe0c323c1c2c36bc95a8695a67f9f86520e9)
BibTeX
@misc{dcca893b1dcba9,
  title = {Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation — arXiv:2609.04484},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04484},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca893b1dcba9; sha256 8e8b46e6a53414fea4229e9f3eecbe0c323c1c2c36bc95a8695a67f9f86520e9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04484. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper investigates structural priming in language model (LM) production, examining how preceding structural context influences sentence completion. While prior work has demonstrated priming effects in comprehension of structural alternations, it remained unclear whether these persist in production, where, when generating, an LM samples from many possible continuations at each step. We address this question through a series of controlled sentence-completion experiments on dative constructions. In line with prior work, we find that LMs are susceptible to structural priming, particularly in sentences that are semantically coherent. In terms of priming magnitude, we find that while there is a greater relative increase of double-object datives against our baselines, in line with inverse frequency effects, there is a larger absolute increase in prepositional-objects, the more frequently produced construction. Finally, we not only observe that structural priming is boosted by lexico-semantic coherence, but that structurally primed completions display greater levels of lexico-semantic repetition. Taken together, our evidence supports the view that structural priming in LMs operates across multiple levels of linguistic representation, facilitating, and facilitated by syntactic, lexical, and semantic alignment. Code: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.04484 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T22:18:11.495Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).