We introduce TeMLM, a set of transparency-first release artifacts for clinical language models. TeMLM unifies provenance, data transparency, modeling transparency, and governance into a single, machine-checkable release bundle. We define an artifact suite (TeMLM-Card, TeMLM-Datasheet, TeMLM-Provenance) and a lightweight conformance checklist for repeatable auditing. We instantiate the artifacts on Technetium-I, a large-scale synthetic clinical NLP dataset with 498,000 notes, 7.74M PHI entity annotations across 10 types, and ICD-9-CM diagnosis labels, and report reference results for ProtactiniumBERT (about 100 million parameters) on PHI de-identification (token classification) and top-50 ICD-9 code extraction (multi-label classification). We emphasize that synthetic benchmarks are valuable for tooling and process validation, but models should be validated on real clinical data prior to deployment.
@article{arxiv.2601.19191,
title = {Transparency-First Medical Language Models: Datasheets, Model Cards, and End-to-End Data Provenance for Clinical NLP},
author = {Olaf Yunus Laitinen Imanov and Taner Yilmaz and Ayse Tuba Tugrul and Melike Nesrin Zaman and Ozkan Gunalp and Duygu Erisken and Sila Burde Dulger and Rana Irem Turhan and Izzet Ozdemir and Derya Umut Kulali and Ozan Akbulut and Harun Demircioglu and Hasan Basri Kara and Berfin Tavan},
journal= {arXiv preprint arXiv:2601.19191},
year = {2026}
}
Comments
12 pages, 9 figures, 15 tables. Technetium-I case study and ProtactiniumBERT-100M reference benchmarks