Metraipolis › archive › dc_1403e1dd616b
Generating Clinical Vignettes that Preserve Cognitive Formulations — arXiv:2608.29995
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29995
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:52:20.065Z
- SHA-256 of the archived text
0252fee80308442e9e41c6c7d9a2514e74dc477d87c913e6eebf07d5e6a43aed- Stable URL of this page
https://metraipolis.com/documento/dc_1403e1dd616b
How to cite
Generating Clinical Vignettes that Preserve Cognitive Formulations — arXiv:2608.29995 — arXiv (en), https://arxiv.org/abs/2608.29995 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1403e1dd616b (Metraipolis archive dc_1403e1dd616b, sha256 0252fee80308442e9e41c6c7d9a2514e74dc477d87c913e6eebf07d5e6a43aed)
BibTeX
@misc{dc1403e1dd616b,
title = {Generating Clinical Vignettes that Preserve Cognitive Formulations — arXiv:2608.29995},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29995},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1403e1dd616b; sha256 0252fee80308442e9e41c6c7d9a2514e74dc477d87c913e6eebf07d5e6a43aed},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29995. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models can generate fluent clinical case vignettes, but fluency alone does not ensure fidelity to a specifiable clinical structure. We introduce FORMA, a theory-grounded framework that compiles a cognitive model of a disorder into a directed weighted graph, samples a person-specific configuration of that graph, and validates whether the generated vignette preserves the specified components and causal links. We instantiate FORMA on Posttraumatic Stress Disorder using the Ehlers and Clark cognitive model, generating 16,500 vignettes across 500 personas, 11 generation models, and three ablation conditions. Evaluation combines an external edge-recovery probe, two clinical experts, a scaled LLM judge, and a clinician user study with 100 licensed practitioners. The cognitive graph is recoverable from full-condition vignettes (MCC = +0.41, AUC = 0.70) but not from zero-shot generation (MCC = +0.01, AUC = 0.50). Experts rate full vignettes substantially higher than zero-shot alternatives, and clinicians perceive them to be human-written 85% of the time, compared with 22% for zero-shot. FORMA also reduces demographic disparity in perceived quality by 1.5-7x. These results show that cognitive formulation can serve as an auditable specification for scalable synthetic clinical text generation. A repository with the data and code is available online: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.29995 — 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 2026-10-17T07:28:26.812Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).