@article{rohr-etal-2026-deepicd,
    title = "{D}eep{ICD}-R1: Medical Reasoning through Hierarchical Rewards and Unsupervised Distillation",
    author = {R{\"o}hr, Tom  and
      Steffek, Thomas Maximilian Josef  and
      Teucher, Roman  and
      Bressem, Keno  and
      Figueroa, Alexei  and
      Grundmann, Paul  and
      Troeger, Peter  and
      Gers, Felix Alexander  and
      L{\"o}ser, Alexander},
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.843/",
    pages = "10764--10775",
    abstract = "Large language models (LLMs) show strong reasoning abilities, but full retraining for the medical domain is often infeasible because of lacking data or compute resources. We present DeepICD-R1, a framework for efficient medical reasoning fine-tuning that unites hierarchical rewards with distilled supervision. We reformulate ICD-10-CM prediction as a reinforcement learning problem and design a hierarchical outcome-based reward that reflects the ICD code structure across chapter, category, and full-code levels. In parallel, we publish a large-scale distilled dataset of over 90k reasoning traces derived from MIMIC-IV admission notes, integrating clinical validation and official coding guidelines. Fine-tuning smaller instruction-tuned LLMs with this data and GRPO reinforcement yields consistent gains in diagnostic accuracy and reasoning coherence. Extensive ablations confirm that hierarchical supervision and verifiable outcome rewards enable competitive, domain-specialized reasoning models without additional pretraining, providing a reproducible foundation for clinical NLP research. Keywords: Clinical NLP, Large Reasoning Model, GRPO, Supervised Fine-Tuning"
}