@inproceedings{liu-reiter-2026-linguistically,
    title = "Linguistically-Informed Evaluation of {LLM}s on Acceptability Judgments in a Forced-Choice Paradigm",
    author = "Liu, Ziyue  and
      Reiter, Nils",
    editor = "T.Y.S.S., Santosh  and
      Rodriguez, Juan Diego  and
      de Gibert, Ona",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-srw.103/",
    pages = "1177--1189",
    ISBN = "979-8-89176-393-7",
    abstract = "Evaluating the grammatical abilities of large language models (LLMs) is important for both NLP and linguistic theory. We investigate the ability of large language models (LLMs) to perform acceptability judgments in a forced-choice paradigm. We evaluate a subset of LLMs on 150 minimal sentence pairs sampled from Linguistic Inquiry and categorized using BLiMP linguistic phenomena. Our results show that while LLMs approximate human judgments, performance varies across models and phenomenon types, with stronger alignment on morphosyntactic phenomena than on linguistically and semantically demanding phenomena. Prompting strategies have minimal impact."
}