ACL 2024findings4 citations

Views Are My Own, but Also Yours: Benchmarking Theory of Mind Using Common Ground

Adil Soubki, John Murzaku, Arash Yousefi Jordehi, Peter Zeng, Magdalena Markowska, Seyed Abolghasem Mirroshandel, Owen Rambow

Abstract

Evaluating the theory of mind (ToM) capabilities of language models (LMs) has recently received a great deal of attention. However, many existing benchmarks rely on synthetic data, which risks misaligning the resulting experiments with human behavior. We introduce the first ToM dataset based on naturally occurring spoken dialogs, Common-ToM, and show that LMs struggle to demonstrate ToM. We then show that integrating a simple, explicit representation of beliefs improves LM performance on Common-ToM.

BibTeX
@inproceedings{soubki-etal-2024-views,
    title = "Views Are My Own, but Also Yours: Benchmarking Theory of Mind Using Common Ground",
    author = "Soubki, Adil  and
      Murzaku, John  and
      Yousefi Jordehi, Arash  and
      Zeng, Peter  and
      Markowska, Magdalena  and
      Mirroshandel, Seyed Abolghasem  and
      Rambow, Owen",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-acl.880/",
    doi = "10.18653/v1/2024.findings-acl.880",
    pages = "14815--14823"
}
Views Are My Own, but Also Yours: Benchmarking Theory of Mind Using Common Ground · ACL 2024