English

A Discerning Several Thousand Judgments: GPT-3 Rates the Article + Adjective + Numeral + Noun Construction

Computation and Language 2023-02-07 v2

Abstract

Knowledge of syntax includes knowledge of rare, idiosyncratic constructions. LLMs must overcome frequency biases in order to master such constructions. In this study, I prompt GPT-3 to give acceptability judgments on the English-language Article + Adjective + Numeral + Noun construction (e.g., "a lovely five days"). I validate the prompt using the CoLA corpus of acceptability judgments and then zero in on the AANN construction. I compare GPT- 3's judgments to crowdsourced human judgments on a subset of sentences. GPT-3's judgments are broadly similar to human judgments and generally align with proposed constraints in the literature but, in some cases, GPT-3's judgments and human judgments diverge from the literature and from each other.

Keywords

Cite

@article{arxiv.2301.12564,
  title  = {A Discerning Several Thousand Judgments: GPT-3 Rates the Article + Adjective + Numeral + Noun Construction},
  author = {Kyle Mahowald},
  journal= {arXiv preprint arXiv:2301.12564},
  year   = {2023}
}