@inproceedings{sarangi-salam-2026-small,
    title = "Can Small {LLM}s Learn a Robust Theory of Mind via {RLVR}? Investigating Generalization through the False-Belief Task",
    author = "Sarangi, Sneheel  and
      Salam, Hanan",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings 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.findings-acl.2061/",
    pages = "41433--41448",
    ISBN = "979-8-89176-395-1"
}