{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T04:04:33Z","timestamp":1747454673104,"version":"3.40.5"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643685960","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T00:00:00Z","timestamp":1747267200000},"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":[[2025,5,15]]},"abstract":"<jats:p>Anorexia Nervosa (AN) is a severe eating disorder requiring interventions that effectively involve the entire family. Family-Based Therapy (FBT) has shown promise, yet traditional training methods for caregivers can be time-consuming and challenging. We present a serious game leveraging large language models (LLMs) that generate realistic, scenario-based dialogues between caregivers and teens with AN, offering a safe space to practice supportive communication strategies. To enhance the credibility and therapeutic relevance of these generated dialogues, we utilize a few-shot learning approach informed by domain expert feedback, enabling the model to produce contextually accurate and empathetic exchanges. By iteratively refining the system prompt with expert-validated examples, we substantially improve dialogue authenticity without the need for extensive model retraining. This approach provides a scalable, flexible solution that can be adapted to various therapeutic scenarios, ultimately broadening the reach and efficacy of digital health interventions.<\/jats:p>","DOI":"10.3233\/shti250500","type":"book-chapter","created":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T08:58:38Z","timestamp":1747385918000},"source":"Crossref","is-referenced-by-count":0,"title":["Mixing Expert Knowledge with LLM to Improve Dialogue in Serious Games for Anorexia Caregivers: A Feasibility Study"],"prefix":"10.3233","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8164-2931","authenticated-orcid":false,"given":"Alexandre","family":"de Masi","sequence":"first","affiliation":[{"name":"University Hospitals of Geneva, Geneva, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0982-7279","authenticated-orcid":false,"given":"Halit","family":"Mislimi","sequence":"additional","affiliation":[{"name":"University of Geneva, Geneva, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9734-3242","authenticated-orcid":false,"given":"Fr\u00e9d\u00e9ric","family":"Ehrler","sequence":"additional","affiliation":[{"name":"University Hospitals of Geneva, Geneva, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4565-8805","authenticated-orcid":false,"given":"Nicolas","family":"Szilas","sequence":"additional","affiliation":[{"name":"University of Geneva, Geneva, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Studies in Health Technology and Informatics","Intelligent Health Systems \u2013 From Technology to Data and Knowledge"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/SHTI250500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T08:58:38Z","timestamp":1747385918000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/SHTI250500"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,15]]},"ISBN":["9781643685960"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/shti250500","relation":{},"ISSN":["0926-9630","1879-8365"],"issn-type":[{"value":"0926-9630","type":"print"},{"value":"1879-8365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,15]]}}}