@inproceedings{hu-etal-2025-define,
    title = "{D}e{F}ine: Decision-Making with Analogical Reasoning over Factor Profiles",
    author = "Hu, Yebowen  and
      Wang, Xiaoyang  and
      Yao, Wenlin  and
      Lu, Yiming  and
      Zhang, Daoan  and
      Foroosh, Hassan  and
      Yu, Dong  and
      Liu, Fei",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.238/",
    pages = "4587--4603",
    ISBN = "979-8-89176-256-5",
    abstract = "LLMs are ideal for decision-making thanks to their ability to reason over long contexts. However, challenges arise when processing speech transcripts that describe complex scenarios, as they are verbose and include repetition, hedging, and vagueness. E.g., during a company{'}s earnings call, an executive might project a positive revenue outlook to reassure investors, despite uncertainty regarding future earnings. It is crucial for LLMs to incorporate this uncertainty systematically when making decisions. In this paper, we introduce DeFine, a modular framework that constructs probabilistic factor profiles from complex scenarios. It then integrates these profiles with analogical reasoning, leveraging insights from similar past experiences to guide LLMs in making critical decisions in new situations. Our framework separates the tasks of quantifying uncertainty and incorporating it into LLM decision-making. This approach is particularly useful in areas such as consulting and financial deliberation, where making decisions under uncertainty is vital."
}