Metraipolis › archive › dc_4b5f69fbbf44

Prompting is not enough: supervised baselines and leakage control for measuring shared decision-making with LLMs in pediatric encounters — arXiv:2608.14792

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14792
License (as archived)
CC0-1.0
Archived
2026-10-18T17:55:44.675Z
SHA-256 of the archived text
e91b337f51364b951df8c71a6f69cabc640a1aaf4c5d418e2e63aeb680675de7
Stable URL of this page
https://metraipolis.com/documento/dc_4b5f69fbbf44

How to cite

Prompting is not enough: supervised baselines and leakage control for measuring shared decision-making with LLMs in pediatric encounters — arXiv:2608.14792 — arXiv (en), https://arxiv.org/abs/2608.14792 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4b5f69fbbf44 (Metraipolis archive dc_4b5f69fbbf44, sha256 e91b337f51364b951df8c71a6f69cabc640a1aaf4c5d418e2e63aeb680675de7)
BibTeX
@misc{dc4b5f69fbbf44,
  title = {Prompting is not enough: supervised baselines and leakage control for measuring shared decision-making with LLMs in pediatric encounters — arXiv:2608.14792},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14792},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4b5f69fbbf44; sha256 e91b337f51364b951df8c71a6f69cabc640a1aaf4c5d418e2e63aeb680675de7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14792. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Objectives: To determine whether zero-shot prompting of a large language model (LLM) is sufficient to detect shared decision-making (SDM) behaviors in real clinical encounters, and whether supervised learning adds value under patient-grouped, nested evaluation. Methods: We analyzed 21 audio-recorded outpatient surgical decision encounters (19 unique patients; 7,566 utterance segments; ~6.1 hours) between families of children with multiple long-term conditions and their surgical providers. Trained coders labeled segments for 12 SDM behaviors (human-human macro Cohen's kappa = 0.695). We compared a zero-shot local LLM (Qwen 2.5 32B), a supervised classifier over frozen sentence embeddings, and their logistic stack, under patient-grouped outer folds with inner cross-fitted thresholds and patient-resampled confidence intervals. Results: The zero-shot LLM reached macro kappa = 0.139 (95% CI 0.111-0.164). The supervised classifier reached kappa = 0.227 (0.186-0.262), a paired improvement of 0.088 (0.051-0.119). A logistic stack of the two reached kappa = 0.242 (0.198-0.284). We identified multiple corpus-specific leakage paths, including grouping sibling recordings separately and allowing labels from an outer held-out patient to enter few-shot exemplars used while fitting downstream models. Conclusion: Zero-shot prompting alone is not sufficient to measure SDM behavior as reliably as a small supervised model, and patient-level grouping alone does not prevent leakage when labeled prompt exemplars are precomputed outside the outer evaluation loop. Reported performance is sensitive to the unit of data splitting and to where labeled exemplars enter the pipeline. External validation is needed before these findings generalize beyond this population, model, prompt, and codebook.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.14792 — 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 2026-10-18T16:29:13.959Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).