@inproceedings{lam-etal-2025-leveraging,
    title = "Leveraging Human Production-Interpretation Asymmetries to Test {LLM} Cognitive Plausibility",
    author = "Lam, Suet-Ying  and
      Zeng, Qingcheng  and
      Wu, Jingyi  and
      Voigt, Rob",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-short.14/",
    pages = "158--171",
    ISBN = "979-8-89176-252-7",
    abstract = "Whether large language models (LLMs) process language similarly to humans has been the subject of much theoretical and practical debate. We examine this question through the lens of the production-interpretation distinction found in human sentence processing and evaluate the extent to which instruction-tuned LLMs replicate this distinction. Using an empirically documented asymmetry between pronoun production and interpretation in humans for implicit causality verbs as a testbed, we find that some LLMs do quantitatively and qualitatively reflect human-like asymmetries between production and interpretation. We demonstrate that whether this behavior holds depends upon both model size-with larger models more likely to reflect human-like patterns and the choice of meta-linguistic prompts used to elicit the behavior. Our codes and results are available here."
}