@inproceedings{roberts-etal-2025-large,
    title = "Do Large Language Models Learn Human-Like Strategic Preferences?",
    author = "Roberts, Jesse  and
      Moore, Kyle  and
      Fisher, Douglas",
    editor = "Kamalloo, Ehsan  and
      Gontier, Nicolas  and
      Lu, Xing Han  and
      Dziri, Nouha  and
      Murty, Shikhar  and
      Lacoste, Alexandre",
    booktitle = "Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.realm-1.8/",
    doi = "10.18653/v1/2025.realm-1.8",
    pages = "97--108",
    ISBN = "979-8-89176-264-0",
    abstract = "In this paper, we evaluate whether LLMs learn to make human-like preference judgements in strategic scenarios as compared with known empirical results. Solar and Mistral are shown to exhibit stable value-based preference consistent with humans and exhibit human-like preference for cooperation in the prisoner{'}s dilemma (including stake-size effect) and traveler{'}s dilemma (including penalty-size effect). We establish a relationship between model size, value-based preference, and superficiality. Finally, results here show that models tending to be less brittle have relied on sliding window attention suggesting a potential link. Additionally, we contribute a novel method for constructing preference relations from arbitrary LLMs and support for a hypothesis regarding human behavior in the traveler{'}s dilemma."
}