Metraipolis › archive › dc_025b0bbd7c51

A decision-basis contract for auditable LLM-assisted medical billing verification: deterministic rules, verbatim evidence, and fail-closed abstention — arXiv:2609.12156

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12156
License (as archived)
CC0-1.0
Archived
2026-10-16T03:03:12.229Z
SHA-256 of the archived text
bb9bb8fa698444506a124b09851e7c80d998e1e1e7609abc7e5d2752f5831fe7
Stable URL of this page
https://metraipolis.com/documento/dc_025b0bbd7c51

How to cite

A decision-basis contract for auditable LLM-assisted medical billing verification: deterministic rules, verbatim evidence, and fail-closed abstention — arXiv:2609.12156 — arXiv (en), https://arxiv.org/abs/2609.12156 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_025b0bbd7c51 (Metraipolis archive dc_025b0bbd7c51, sha256 bb9bb8fa698444506a124b09851e7c80d998e1e1e7609abc7e5d2752f5831fe7)
BibTeX
@misc{dc025b0bbd7c51,
  title = {A decision-basis contract for auditable LLM-assisted medical billing verification: deterministic rules, verbatim evidence, and fail-closed abstention — arXiv:2609.12156},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12156},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_025b0bbd7c51; sha256 bb9bb8fa698444506a124b09851e7c80d998e1e1e7609abc7e5d2752f5831fe7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12156. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This work presents a proof of concept for auditable LLM-assisted medical billing verification based on a decision-basis contract. The contract separates deterministic checks of versioned fee-catalog rules from LLM-based assessment of free-text documentation. The deterministic layer resolves the applicable catalog release and checks code availability, quantity limits, and exclusions. The semantic layer classifies each claimed item as supported, contradicted, or missing required information. Support and contradiction require a verbatim evidence span; unavailable rule context, unsuccessful assessment, or missing required evidence prevents support through fail-closed abstention. We evaluated four locally run open-weight models on a synthetic catalog and 36 curated cases under the contract, an ablation without explicit documentation requirements, and an end-to-end baseline. Outcome agreement varied across models and showed no consistent advantage over the baseline. Explicit documentation requirements improved identification of missing information for all four models. The evidence gate also exposed cases in which correct raw judgments lacked valid evidence and were converted to incomplete decision-basis entries. The results show how explicit decision records can make rule findings, documentation judgments, and abstention reasons inspectable. Evaluation on real catalogs, independently annotated documentation, and with human reviewers is required to assess practical value.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.12156 — 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 2026-10-16T02:51:27.865Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).