{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T10:50:27Z","timestamp":1782989427854,"version":"3.54.5"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686684","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,29]]},"abstract":"<jats:p>We benchmarked five open-source LLMs (12\u201324B parameters) on ICHD-3 headache classification using 305 synthetic vignettes from the HeadAI dataset. Five standard prompting techniques achieved 56\u201361% top-1 accuracy with no significant pairwise differences. A three-tier oracle ablation that progressively provided the correct diagnosis reached 81\u201394%, revealing a 36-percentage-point gap attributable to retrieval quality. When the retriever placed the correct diagnosis at rank 1 (Hit@1 = 23%), accuracy reached 94.9%. The gap decomposed into retrieval quality (\u223c24 pp), noise (\u223c6 pp), and intra-category differentiation (\u223c6 pp). Rule application is not the bottleneck; knowledge delivery is.<\/jats:p>","DOI":"10.3233\/shti260922","type":"book-chapter","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T10:03:14Z","timestamp":1782986594000},"source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Prompting Strategies for Open-Source Language Models in ICHD-3 Headache Classification"],"prefix":"10.3233","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0990-3570","authenticated-orcid":false,"given":"Dorian","family":"Zwanzig","sequence":"first","affiliation":[{"name":"Eberswalde University for Sustainable Development, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"7437","container-title":["Studies in Health Technology and Informatics","Health Sciences Informatics Leads and Empowers the Digital Health Transformation"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/SHTI260922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T10:03:14Z","timestamp":1782986594000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/SHTI260922"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"ISBN":["9781643686684"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/shti260922","relation":{},"ISSN":["0926-9630","1879-8365"],"issn-type":[{"value":"0926-9630","type":"print"},{"value":"1879-8365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,29]]}}}