@inproceedings{lei-etal-2026-unified,
    title = "A Unified Framework for Modeling Heterogeneous Financial Data via Dual-Granularity Prompting",
    author = "Lei, Yu  and
      Wang, Zixuan  and
      Feng, Yiqing  and
      Zhang, Junru  and
      Li, Yahui  and
      Chu, LIU  and
      Tongyao, Wang  and
      Li, Dongyang",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.43/",
    pages = "618--631",
    ISBN = "979-8-89176-394-4",
    abstract = "Recent industrial credit scoring models remain heavily reliant on manually tuned statistical learning methods. Despite their potential, deep learning architectures have struggled to consistently outperform traditional statistical models in industrial credit scoring, largely due to the complexity of heterogeneous financial data and the challenge of modeling evolving creditworthiness. To bridge this gap, we introduce FinLangNet, a novel framework that reformulates credit scoring as a multi-scale sequential learning problem. FinLangNet processes heterogeneous financial data through a dual-module architecture that combines tabular feature extraction with temporal sequence modeling, generating probability distributions of users' future financial behaviors across multiple time horizons. A key innovation is our dual-prompt mechanism within the sequential module, which introduces learnable prompts operating at both feature-level granularity for capturing fine-grained temporal patterns and user-level granularity for aggregating holistic risk profiles. Notably, real world deployment yielded a 6.3 pp improvement in KS, along with a 9.9{\%} reduction in bad debt rate."
}