Metraipolis › archive › dc_fa7a1af3fb77
SDoH-Aware Narrative Anchoring Bias in Medical LLMs for Trustworthy Clinical Decision Support — arXiv:2608.22802
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.22802
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:45:03.124Z
- SHA-256 of the archived text
9a0d7c9ca5c86df92779db19f0f47efb7352d4eda9fa8471a212df121af1d317- Stable URL of this page
https://metraipolis.com/documento/dc_fa7a1af3fb77
How to cite
SDoH-Aware Narrative Anchoring Bias in Medical LLMs for Trustworthy Clinical Decision Support — arXiv:2608.22802 — arXiv (en), https://arxiv.org/abs/2608.22802 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa7a1af3fb77 (Metraipolis archive dc_fa7a1af3fb77, sha256 9a0d7c9ca5c86df92779db19f0f47efb7352d4eda9fa8471a212df121af1d317)
BibTeX
@misc{dcfa7a1af3fb77,
title = {SDoH-Aware Narrative Anchoring Bias in Medical LLMs for Trustworthy Clinical Decision Support — arXiv:2608.22802},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.22802},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa7a1af3fb77; sha256 9a0d7c9ca5c86df92779db19f0f47efb7352d4eda9fa8471a212df121af1d317},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22802. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Medical large language models are often judged by how many clinical questions they answer correctly. That view is useful, but it misses a practical risk. A model may know the right answer and still change its response when the same case is written in a different patient voice. This paper evaluates that risk as SDoH aware narrative anchoring bias. We use NarrativeShield SDoH MedQA, a counterfactual medical question answering dataset in which each case appears in persona based narratives while the answer key remains fixed. The dataset is reshaped from wide format into case grouped persona rows. We evaluate three open source instruction tuned LLMs from the Qwen2.5 family: 1.5B, 3B, and 7B. The final experiment uses 300 clinical cases and produces 8,100 model responses across three prompting conditions. We report persona level accuracy, counterfactual consistency, correct consistency, and narrative sensitivity error. Qwen2.5 7B achieves the best accuracy at 56.33 percent and the best correct consistency at 40.33 percent. Paired McNemar exact tests show significant accuracy gains for 7B over 3B in all prompt settings. Even so, narrative sensitivity remains, with the lowest error still at 31.67 percent. These results suggest that trustworthy clinical decision support should be evaluated by both average correctness and stability across medically equivalent patient narratives. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.22802 — 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 2026-10-18T07:37:52.901Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).