@inproceedings{mahowald-2023-discerning,
    title = "A Discerning Several Thousand Judgments: {GPT}-3 Rates the Article + Adjective + Numeral + Noun Construction",
    author = "Mahowald, Kyle",
    editor = "Vlachos, Andreas  and
      Augenstein, Isabelle",
    booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
    month = may,
    year = "2023",
    address = "Dubrovnik, Croatia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.eacl-main.20/",
    doi = "10.18653/v1/2023.eacl-main.20",
    pages = "265--273",
    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."
}