Metraipolis › archive › dc_0e944cdcbcd9

Whose doctor does the AI recommend? An algorithm audit of reputation and demographic signals in large language model-assisted physician choice — arXiv:2608.14399

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.14399
License (as archived): CC0-1.0
Archived: 2026-10-19T02:21:31.567Z
SHA-256 of the archived text: c5cccf6a4a0b70b532ea31e2800ce8d1f8213d8eda2d5b67d87a9b0e1bcf87a0
Stable URL of this page: https://metraipolis.com/documento/dc_0e944cdcbcd9

How to cite

Whose doctor does the AI recommend? An algorithm audit of reputation and demographic signals in large language model-assisted physician choice — arXiv:2608.14399 — arXiv (en), https://arxiv.org/abs/2608.14399 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0e944cdcbcd9 (Metraipolis archive dc_0e944cdcbcd9, sha256 c5cccf6a4a0b70b532ea31e2800ce8d1f8213d8eda2d5b67d87a9b0e1bcf87a0)

BibTeX

@misc{dc0e944cdcbcd9,
  title = {Whose doctor does the AI recommend? An algorithm audit of reputation and demographic signals in large language model-assisted physician choice — arXiv:2608.14399},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14399},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0e944cdcbcd9; sha256 c5cccf6a4a0b70b532ea31e2800ce8d1f8213d8eda2d5b67d87a9b0e1bcf87a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14399. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Patients increasingly ask large language model (LLM) assistants which doctor to see, making these systems AI infomediaries: algorithms that intermediate one person's choice among other people and thereby decide, silently and at scale, which physicians become visible. We report a prespecified randomized algorithm audit of what causally moves those recommendations. Seven models (six open-weight; gpt-4o-mini) each chose among five synthetic family-medicine physician cards whose attributes were independently randomized across 3,024 choice sets, three patient personas, nine prompt paraphrases and nine experimental arms, yielding 40,068 scored responses; gender and ethnicity were signaled through names following correspondence-audit methodology. Reputation signals dominate: raising a rating from 3.9 to 4.7 increases choice probability by 31.4 percentage points (pp), and raising the fee from $90 to $190 lowers it by 20.0 pp. Demographic parity is rejected, but not in the direction human audit studies predict: female-signaled names gain 2.5 pp, and Hispanic-, South-Asian- and Black-signaled names gain 1.3-2.9 pp over White-signaled names, tilts worth $7-$14 per visit in fee-equivalent terms, and a content-free first-listed position is worth $11. Yet models mentioned gender or ethnicity in at most 0.03% of their stated reasons and abstained in 0.39% of trials, so these effects are invisible in the models' own explanations, and transparency obligations relying on model self-report would not detect them. One reasoning model failed the prespecified auditability gate outright. The frozen design makes the audit repeatable: any new model can be assessed against identical stimuli, making recurring behavioural audit, rather than self-reported explanation, the monitoring technology fit for purpose.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI).
Categorie arXiv: Computers and Society (cs.CY) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.14399 — 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 2026-10-19T02:02:02.947Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).