@inproceedings{spinoso-di-piano-etal-2025-rsa,
    title = "({RSA}){\texttwosuperior}: A Rhetorical-Strategy-Aware Rational Speech Act Framework for Figurative Language Understanding",
    author = "Spinoso-Di Piano, Cesare  and
      Austin, David Eric  and
      Piantanida, Pablo  and
      Cheung, Jackie CK",
    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 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1019/",
    pages = "20898--20938",
    ISBN = "979-8-89176-251-0",
    abstract = "Figurative language (e.g., irony, hyperbole, understatement) is ubiquitous in human communication, resulting in utterances where the literal and the intended meanings do not match. The Rational Speech Act (RSA) framework, which explicitly models speaker intentions, is the most widespread theory of probabilistic pragmatics, but existing implementations are either unable to account for figurative expressions or require modeling the implicit motivations for using figurative language (e.g., to express joy or annoyance) in a setting-specific way. In this paper, we introduce the Rhetorical-Strategy-Aware RSA (RSA){\texttwosuperior} framework which models figurative language use by considering a speaker{'}s employed rhetorical strategy. We show that (RSA){\texttwosuperior} enables human-compatible interpretations of non-literal utterances without modeling a speaker{'}s motivations for being non-literal. Combined with LLMs, it achieves state-of-the-art performance on the ironic split of PragMega+, a new irony interpretation dataset introduced in this study."
}