@inproceedings{he-etal-2026-idea,
    title = "{IDEA}: An Interpretable and Editable Decision-Making Framework for {LLM}s via Verbal-to-Numeric Calibration",
    author = "He, Yanji  and
      Jiang, Yuxin  and
      Wu, Yiwen  and
      Huang, Bo  and
      Wei, Jiaheng  and
      Wang, Wei",
    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.2004/",
    pages = "40312--40332",
    ISBN = "979-8-89176-395-1",
    abstract = "Large Language Models are increasingly deployed for decision-making, yet their adoption in high-stakes domains remains limited by miscalibrated probabilities, unfaithful explanations, and inability to incorporate expert knowledge precisely. We propose **IDEA**, a framework that extracts LLM decision knowledge into an interpretable parametric model over semantically meaningful factors. Through joint learning of verbal-to-numerical mappings and decision parameters via EM, correlated sampling that preserves factor dependencies, and direct parameter editing with mathematical guarantees, IDEA produces calibrated probabilities while enabling quantitative human-AI collaboration. Experiments across five datasets show IDEA with Qwen-3-32B (78.6{\%}) outperforms DeepSeek R1 (68.1{\%}) and GPT-5.2 (77.9{\%}), achieving perfect factor exclusion and exact calibration{---}precision unattainable through prompting alone."
}