Metraipolis › archive › dc_833d68732ef7

Making every stage of medical device document assessment with large language models deterministic — arXiv:2610.21300

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21300
License (as archived)
CC0-1.0
Archived
2026-10-16T09:55:57.758Z
SHA-256 of the archived text
b4c1996cb1e1dd12c3acc1893f77220fcca919bbea8fd981b4d68f274eb4ff29
Stable URL of this page
https://metraipolis.com/documento/dc_833d68732ef7

How to cite

Making every stage of medical device document assessment with large language models deterministic — arXiv:2610.21300 — arXiv (en), https://arxiv.org/abs/2610.21300 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_833d68732ef7 (Metraipolis archive dc_833d68732ef7, sha256 b4c1996cb1e1dd12c3acc1893f77220fcca919bbea8fd981b4d68f274eb4ff29)
BibTeX
@misc{dc833d68732ef7,
  title = {Making every stage of medical device document assessment with large language models deterministic — arXiv:2610.21300},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21300},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_833d68732ef7; sha256 b4c1996cb1e1dd12c3acc1893f77220fcca919bbea8fd981b4d68f274eb4ff29},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21300. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

To show that a medical device complies with regulation, experts judge whether documents and records meet each requirement and record the judgment for others to verify. For each assessment item that experts define, large language models could prepare a preliminary assessment: a label such as Satisfied or Not satisfied, a reason and quoted evidence. We sent fourteen commercial deployments of such models (seven models from three providers, through six routes) the same request repeatedly, with the deterministic sampling settings each accepted; every deployment returned differing assessments for at least one request, and in twelve the label changed. Reducing reasoning where the interface allows it did not reduce the variation, and prompts of retrieved passages removed it only for the smallest models. The same open-weight model was reproducible or not depending only on how it was served. A pipeline we built to be deterministic at every stage -- text extraction and optical character recognition (OCR), chunking, embedding, indexing, retrieval and inference -- returned byte-identical output at each stage across reruns, interruptions, edits, machines of one graphics processing unit (GPU) model and days, for blood glucose meter and infusion pump documents. OCR, embedding and approximate retrieval varied when their own serving was not made invariant, and outputs changed with the GPU model and with the inference engine's scheduling settings, which therefore belong in the recorded configuration. End-to-end determinism is achievable and gives a testable basis for audit and change control.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.21300 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T08:44:47.636Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).