@inproceedings{chen-etal-2025-decisionflow,
    title = "{D}ecision{F}low: Advancing Large Language Model as Principled Decision Maker",
    author = "Chen, Xiusi  and
      Wang, Shanyong  and
      Qian, Cheng  and
      Wang, Hongru  and
      Han, Peixuan  and
      Ji, Heng",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.905/",
    doi = "10.18653/v1/2025.findings-emnlp.905",
    pages = "16668--16692",
    ISBN = "979-8-89176-335-7",
    abstract = "In high-stakes domains such as healthcare and finance, effective decision-making demands not just accurate outcomes but transparent and explainable reasoning. However, current language models often lack the structured deliberation needed for such tasks, instead generating decisions and justifications in a disconnected, post-hoc manner. To address this, we propose DecisionFlow, a novel decision modeling framework that guides models to reason over structured representations of actions, attributes, and constraints. Rather than predicting answers directly from prompts, DecisionFlow builds a semantically grounded decision space and infers a latent utility function to evaluate trade-offs in a transparent, utility-driven manner. This process produces decisions tightly coupled with interpretable rationales reflecting the model{'}s reasoning. Empirical results on two high-stakes benchmarks show that DecisionFlow not only achieves up to 30{\%} accuracy gains over strong prompting baselines but also enhances alignment in outcomes. Our work is a critical step toward integrating symbolic reasoning with LLMs, enabling more accountable, explainable, and reliable LLM decision support systems. Code and data are at https://github.com/xiusic/DecisionFlow."
}