Metraipolis › archive › dc_ac3a2ebf0a58
Same Facts, Different Updates: Inference Setup Shapes LLM Behavior in Medical Allocation — arXiv:2608.18108
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.18108
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T13:43:16.354Z
- SHA-256 of the archived text
fb3d4d7204a82370e6400cd35340daa3d32fd8d0aa811bdbaba99672e86a5870- Stable URL of this page
https://metraipolis.com/documento/dc_ac3a2ebf0a58
How to cite
Same Facts, Different Updates: Inference Setup Shapes LLM Behavior in Medical Allocation — arXiv:2608.18108 — arXiv (en), https://arxiv.org/abs/2608.18108 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ac3a2ebf0a58 (Metraipolis archive dc_ac3a2ebf0a58, sha256 fb3d4d7204a82370e6400cd35340daa3d32fd8d0aa811bdbaba99672e86a5870)
BibTeX
@misc{dcac3a2ebf0a58,
title = {Same Facts, Different Updates: Inference Setup Shapes LLM Behavior in Medical Allocation — arXiv:2608.18108},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.18108},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ac3a2ebf0a58; sha256 fb3d4d7204a82370e6400cd35340daa3d32fd8d0aa811bdbaba99672e86a5870},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18108. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models are being incorporated into sensitive and important decision-making processes across nearly all fields. While prior work studies model bias around inputs and scenario framing, models can also behave in unexpected and undesirable ways due to context accumulated over their deployment. In this work, we study a medical example in which a model is asked to assign resource-allocation probabilities to two people given brief clinical context, and then sees the same scenario with a single extra sentence containing contrasting patient information, either with or without its previous response in context. Across three of four tested models, the paired-context and independent-inference experiments have different probability shifts, often in opposite directions (in favor of Person B vs. in favor of Person A) when new information is provided. We include additional paired-context experiments to show the effect of varying attributes across scenario axes. Our findings show the context-dependent effect of patient information in a sensitive medical use case. More broadly, our work shows the importance of carefully incorporating LLM-based systems into decision-making processes, context engineering, and further model behavioral studies. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.MA). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2608.18108 — 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 2026-10-18T13:40:43.012Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).