Metraipolis › archive › dc_c6fc6dddcffb

Consistent but Biased: Chair Personas Trade Noise for Bias in Multi-Agent Clinical Decisions — arXiv:2610.31325

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.31325
License (as archived): CC0-1.0
Archived: 2026-10-24T10:48:25.181Z
SHA-256 of the archived text: 26fd7851dedb50dc5efacea9fa5da32d3bda25f5abe73d1bd373889e1a0edc06
Stable URL of this page: https://metraipolis.com/documento/dc_c6fc6dddcffb

How to cite

Consistent but Biased: Chair Personas Trade Noise for Bias in Multi-Agent Clinical Decisions — arXiv:2610.31325 — arXiv (en), https://arxiv.org/abs/2610.31325 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c6fc6dddcffb (Metraipolis archive dc_c6fc6dddcffb, sha256 26fd7851dedb50dc5efacea9fa5da32d3bda25f5abe73d1bd373889e1a0edc06)

BibTeX

@misc{dcc6fc6dddcffb,
  title = {Consistent but Biased: Chair Personas Trade Noise for Bias in Multi-Agent Clinical Decisions — arXiv:2610.31325},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31325},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c6fc6dddcffb; sha256 26fd7851dedb50dc5efacea9fa5da32d3bda25f5abe73d1bd373889e1a0edc06},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31325. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In clinical systems built from several large language model (LLM) agents, one agent often chairs the discussion and makes the final decision. Whether the chair's persona prompt changes that decision, or the agreement between repeated runs that some systems treat as reliability, has not been tested with the case held constant. We ask whether the persona changes the decision or only its timing, how it affects agreement between runs, and which behaviors appear when the prompt describes only personality traits. A simulated department of seven agents discussed 20 published cases of degenerative cervical myelopathy, with the case reports replayed unchanged in every run. Only the prompts of the chair and its deputy changed (no persona, or a consultative, autocratic or avoidant one), written either as rules of conduct or as personality traits. With personas written as rules, the chair chose to operate now in 93% of runs when autocratic and in 2% when avoidant, against 57% without a persona. Surgery was still planned in nearly all decisions, so the personas mainly changed whether to operate now or after more tests. These effects held with a second model and reworded prompts. The autocratic and avoidant personas made the three runs of a case agree more often, but only about as often as chance predicts, and Fleiss $\kappa$ did not rise. Prompts that described only personality traits kept more than half of the autocratic and avoidant effects on operating now. They reproduced quick decisions, delays and extra tests, but not ignoring red flags, dropping backup plans or passing the decision to the family. Studies should report and vary the chair's persona as they do the model, and correct agreement between runs for chance before calling it reliability.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.31325 — 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 2026-10-24T10:48:23.948Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).