Quinex and Data Extraction from Scientific Publicationshttps://doi.org/10.26165/JUELICH-DATA/HFGWDBJan GöpfertPatrick KuckertzTitan HartonoJann Michael WeinandJülich DATA2026-09-072026-09-07T07:25:17ZThis presentation introduces Quinex, an open-source framework for the automated extraction of quantitative information from scientific literature. It demonstrates how quantitative statements embedded in publications can be transformed into structured, reusable datasets to support literature analysis, research data management, and data-driven scientific workflows. The presentation was given by Patrick Kuckertz as part of the 90th Jour Fixe FDM organized by fdm.nrw. <h3>Acknowledgements</h3> The authors would like to thank the German Federal Government, the German State Governments, and the Joint Science Conference (GWK) for their funding and support as part of the NFDI4Ing consortium. Funded by the German Research Foundation (DFG) - project number: 442146713. This work was also supported by the Helmholtz Association under the program "Energy System Design".Computer and Information Sciencequantitative information extractionscientific literature miningsmall language modelsautomated literature reviewstructured data extractionscientific NLPGöpfert, Jan, et al. "Quinex: Quantitative information extraction from text using open and lightweight LLMs." The Innovation (2026)., doi, 10.1016/j.xinn.2026.101391, https://doi.org/10.1016/j.xinn.2026.101391Kuckertz, Patrick2026-06-22CCBY