Transparency-First Medical Language Models: Datasheets, Model Cards, and End-to-End Data Provenance for Clinical NLP
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910001920999424 |
|---|---|
| author | Imanov, Olaf Yunus Laitinen Yilmaz, Taner Tugrul, Ayse Tuba Zaman, Melike Nesrin Gunalp, Ozkan Erisken, Duygu Dulger, Sila Burde Turhan, Rana Irem Ozdemir, Izzet Kulali, Derya Umut Akbulut, Ozan Demircioglu, Harun Kara, Hasan Basri Tavan, Berfin |
| author_facet | Imanov, Olaf Yunus Laitinen Yilmaz, Taner Tugrul, Ayse Tuba Zaman, Melike Nesrin Gunalp, Ozkan Erisken, Duygu Dulger, Sila Burde Turhan, Rana Irem Ozdemir, Izzet Kulali, Derya Umut Akbulut, Ozan Demircioglu, Harun Kara, Hasan Basri Tavan, Berfin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_19191 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Transparency-First Medical Language Models: Datasheets, Model Cards, and End-to-End Data Provenance for Clinical NLP Imanov, Olaf Yunus Laitinen Yilmaz, Taner Tugrul, Ayse Tuba Zaman, Melike Nesrin Gunalp, Ozkan Erisken, Duygu Dulger, Sila Burde Turhan, Rana Irem Ozdemir, Izzet Kulali, Derya Umut Akbulut, Ozan Demircioglu, Harun Kara, Hasan Basri Tavan, Berfin Computation and Language Machine Learning 68T50 I.2.7; J.3 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. |
| title | Transparency-First Medical Language Models: Datasheets, Model Cards, and End-to-End Data Provenance for Clinical NLP |
| topic | Computation and Language Machine Learning 68T50 I.2.7; J.3 |
| url | https://arxiv.org/abs/2601.19191 |