@inproceedings{kabra-etal-2026-verifiable,
    title = "Verifiable Financial Enterprise Question Answering via Inference-Time Grounding and Traceability",
    author = "Kabra, Anubha  and
      Kim, Katie Jooyoung  and
      Kou, Zhiwei  and
      Sajer, Helene  and
      Fan, Yimei  and
      Martinez Vidiri, Gabriel",
    editor = "El-Haj, Mo  and
      Moreno Sandoval, Antonio  and
      Garcia-Serrano, Ana  and
      Chen, Chung-Chi  and
      Rayson, Paul  and
      Torterolo Orta, Yanco Amor  and
      Martinez, Paloma  and
      Porta, Jordi",
    booktitle = "The 7th Financial Narrative Processing Workshop",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/revision-workflow/2026.fnp-1.4/",
    doi = "10.63317/25dqodqmcsa4",
    pages = "39--48",
    abstract = "Financial enterprise AI systems deployed in high-stakes settings require responses that are verifiable, traceable, and auditable. We introduce a modular, model- and data-agnostic inference-time control framework, together with a deployment-aware evaluation strategy for verifiable financial enterprise question answering. Our method enforces faithfulness at inference time without retraining or changes to retrieval infrastructure. We deploy our method in a production financial enterprise assistant and evaluate it using a combination of intrinsic faithfulness metrics, baseline comparisons, and real-world user feedback. Our approach improves groundedness by 29{\%} over baselines, reduces hallucinations to near-zero levels, and achieves near-perfect document-span traceability. Together, our results demonstrate that modular pipeline design combined with detailed, deployment-aware evaluation provides a practical and effective path toward verifiable financial enterprise QA systems."
}