EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Constructing understanding: on the constructional information encoded in large language models

Claire Bonial, Harish Tayyar Madabushi

Language Resources and Evaluation · 2025-12 · 59 (4) · 4559-4598

DOI: 10.1007/s10579-024-09799-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Language Resources and Evaluation, online erschienen am 20.12.2024. Verfasst von Claire Bonial und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Early Career Research grant from the University of Bath.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We review research related to both Construction Grammar (CxG) and Natural Language Processing showing that recent advances in probing Large Language Models (LLMs) for certain types of linguistic knowledge align with the tenets of CxG. However, our survey leads us to hypothesize that LLM constructional information may be limited to the constructions within the lower levels of postulated taxonomical “constructicons” enumerating a particular language’s constructions. Specifically, probing studies show that the constructions at the lower levels of the taxonomy, which are more substantive constructions with fixed elements corresponding to frequently used words within that construction, are a type of linguistic information accessible to LLMs. In contrast, more general, abstract constructions with schematic slots that can be filled by a variety of different words are not included in the linguistic knowledge of LLMs. We test this hypothesis on a collection of 10 distinct constructions, each of which is exhibited in 50 or more corpus instances. Our experimental results strongly support our hypothesis and lead us to conclude that, in order for LLMs to generalize to the point where purely schematic constructions can be recognized regardless of the frequency of the instantiating words (as psycholinguistic experimentation has shown people can), additional semantic resources are needed to make explicit the semantic role of the schematic slot. To ensure transparency and reproducibility, we publicly release our experimental data, including the prompts used with the model.

Förderung

  • The Early Career Research grant from the University of Bath

Zitieren

APA

Bonial, C., & Madabushi, H. T. (2025). Constructing understanding: on the constructional information encoded in large language models. Language Resources and Evaluation, 59(4), 4559-4598. https://doi.org/10.1007/s10579-024-09799-9

Vancouver

Bonial C, Madabushi HT. Constructing understanding: on the constructional information encoded in large language models. Language Resources and Evaluation. 2025;59(4):4559-4598. doi:10.1007/s10579-024-09799-9

BibTeX
@article{Bonial2025,
  author = {Bonial, Claire and Madabushi, Harish Tayyar},
  title = {Constructing understanding: on the constructional information encoded in large language models},
  journal = {Language Resources and Evaluation},
  year = {2025},
  volume = {59},
  number = {4},
  pages = {4559--4598},
  doi = {10.1007/s10579-024-09799-9}
}
Kostenlos starten →