{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T21:47:05Z","timestamp":1791928025443,"version":"4.3.4"},"reference-count":19,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["MethodsX"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.mex.2026.104041","type":"journal-article","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T05:51:09Z","timestamp":1783921869000},"page":"104041","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A reproducible optimisation protocol for calibrating prompt-based large language model workflows in evidence synthesis"],"prefix":"10.1016","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9416-1435","authenticated-orcid":false,"given":"Teo","family":"Susnjak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.mex.2026.104041_bib0001","unstructured":"O. Khattab, A. Singhvi, P. Maheshwari, et al., DSPy: compiling declarative language model calls into self-improving pipelines, 2023, arXiv preprint arXiv: 2310.03714."},{"key":"10.1016\/j.mex.2026.104041_bib0002","series-title":"2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024, Hybrid, Miami, United States of America, Nov 12 2024-Nov 16 2024","first-page":"9340","article-title":"Optimizing instructions and demonstrations for multi-stage language model programs","author":"Opsahl-Ong","year":"2024"},{"key":"10.1016\/j.mex.2026.104041_bib0003","unstructured":"L.A. Agrawal, S. Tan, D. Soylu, N. Ziems, R. Khare, K. Opsahl-Ong, A. Singhvi, H. Shandilya, M.J. Ryan, M. Jiang, C. Potts, K. Sen, A.G. Dimakis, I. Stoica, D. Klein, M. Zaharia, O. Khattab, Gepa: reflective prompt evolution can outperform reinforcement learning, 2025. https:\/\/arxiv.org\/abs\/2507.19457."},{"key":"10.1016\/j.mex.2026.104041_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.jclinepi.2025.111746","article-title":"Large language models for conducting systematic reviews: on the rise, but not yet ready for use-a scoping review: on the rise, but not yet ready for use\u2014a scoping review","volume":"181","author":"Lieberum","year":"2025","journal-title":"J. Clin. Epidemiol."},{"key":"10.1016\/j.mex.2026.104041_bib0005","doi-asserted-by":"crossref","DOI":"10.3390\/make7020028","article-title":"Accelerating disease model parameter extraction: an LLM-based ranking approach to select initial studies for literature review automation","volume":"7","author":"Sujau","year":"2025","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"10.1016\/j.mex.2026.104041_bib0006","series-title":"What level of automation is \u201cgood enough\u201d? A benchmark of large language models for meta-analysis data extraction, research synthesis methods","first-page":"1","author":"Li","year":"2026"},{"key":"10.1016\/j.mex.2026.104041_bib0007","unstructured":"L. Li, A. Mathrani, T. Susnjak, Automated risk-of-bias assessment of randomized controlled trials: a first look at a gepa-trained programmatic prompting framework, 2025. https:\/\/arxiv.org\/abs\/2512.01452."},{"issue":"3","key":"10.1016\/j.mex.2026.104041_bib0008","doi-asserted-by":"crossref","DOI":"10.1145\/3715964","article-title":"Automating research synthesis with domain-specific large language model fine-tuning","volume":"19","author":"Susnjak","year":"2025","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"10.1016\/j.mex.2026.104041_bib0009","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"1950","article-title":"Assessing and understanding the prompt sensitivity of LLMs","author":"Zhuo","year":"2024"},{"key":"10.1016\/j.mex.2026.104041_bib0010","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"14550","article-title":"POSIX: a prompt sensitivity index for large language models","author":"Chatterjee","year":"2024"},{"key":"10.1016\/j.mex.2026.104041_bib0011","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1038\/s41586-024-07930-y","article-title":"Larger and more instructable language models become less reliable","volume":"634","author":"Zhou","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.mex.2026.104041_bib0012","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1093\/jamia\/ocae294","article-title":"Establishing best practices in large language model research: an application to repeat prompting","volume":"32","author":"Gallo","year":"2025","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.mex.2026.104041_bib0013","unstructured":"M. Kearns, Responsible ai in the generative era, accessed: 2025-08-01, 2023. https:\/\/www.amazon.science\/blog\/responsible-ai-in-the-generative-era."},{"key":"10.1016\/j.mex.2026.104041_bib0014","series-title":"Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","first-page":"186","article-title":"A reproducibility and generalizability study of large language models for query generation","author":"Staudinger","year":"2024"},{"key":"10.1016\/j.mex.2026.104041_bib0015","series-title":"Proceedings of the Fourth International Conference on Automated Machine Learning","article-title":"Automatic prompt optimization for LLM agents","volume":"293","author":"Spiess","year":"2025"},{"key":"10.1016\/j.mex.2026.104041_bib0016","series-title":"Proceedings of the 39th Conference on Neural Information Processing Systems","article-title":"How to auto-optimize prompts for domain tasks? adaptive prompting and reasoning through evolutionary domain knowledge adaptation","author":"Zhao","year":"2025"},{"key":"10.1016\/j.mex.2026.104041_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.infsof.2022.107128","article-title":"Machine learning in software defect prediction: a business-driven systematic mapping study","volume":"155","author":"Stradowski","year":"2023","journal-title":"Inf. Softw. Technol."},{"key":"10.1016\/j.mex.2026.104041_bib0018","doi-asserted-by":"crossref","unstructured":"A. Huotala, M. Kuutila, M. M\u00e4ntyl\u00e4, SESR-Eval: dataset for evaluating LLMs in the title-abstract screening of systematic reviews, 2025. https:\/\/arxiv.org\/abs\/2507.19027.","DOI":"10.1109\/ESEM64174.2025.00053"},{"key":"10.1016\/j.mex.2026.104041_bib0019","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1136\/jamia.2010.004325","article-title":"A new algorithm for reducing the workload of experts in performing systematic reviews","volume":"17","author":"Matwin","year":"2010","journal-title":"J. Am. Med. Inform. Assoc."}],"container-title":["MethodsX"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2215016126002578?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2215016126002578?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T21:15:31Z","timestamp":1791926131000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2215016126002578"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":19,"alternative-id":["S2215016126002578"],"URL":"https:\/\/doi.org\/10.1016\/j.mex.2026.104041","relation":{},"ISSN":["2215-0161"],"issn-type":[{"value":"2215-0161","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A reproducible optimisation protocol for calibrating prompt-based large language model workflows in evidence synthesis","name":"articletitle","label":"Article Title"},{"value":"MethodsX","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.mex.2026.104041","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104041"}}