@inproceedings{7068,
  abstract     = {Adopting digital twin technologies in small andmedium-sized enterprises (SMEs) is often hinderedby heterogeneous, poorly documented productiondata. Current semantic type detection approachesrequire massive labeled datasets making themimpractical for resource-constrained SMEs. Wepropose a zero-shot hybrid framework combiningpattern-based classification with selective largelanguage model (LLM) reasoning formanufacturing-specific data types. The two-stagearchitecture uses rule-based patterns for high-confidence cases, forwarding ambiguous columnsto a multi-step LLM reasoner. Evaluation on fourmanufacturing datasets shows the hybrid approachachieves weighted F1 within 7 24 percentagepoints of pure LLM classification performancewhile reducing LLM invocations by 39% onaverage. Processing time decreased by up to 2.8×.Our framework addresses a critical gap: automated,computationally efficient data type recognition formanufacturing SMEs without requiring trainingdata, contributing to automated simulation anddigital twin construction.},
  author       = {Döring, Lina and Trojahn, Sebastian and Reusch, Pascal},
  booktitle    = {19th International Doctoral Students Workshop on Logistics, Supply Chain and Production Management},
  editor       = {Behrendt, Fabian and Zadek, Hartmut and Janmontree, Jettarat and Trojahn, Sebastian and Lang, Sebastian},
  keywords     = {Semantic Data Type Detection, DigitalTwin, Manufacturing SMEs, Zero-shot Learning, Hybrid AI, LLM},
  location     = {Magdeburg},
  publisher    = {Otto von Guericke University Library, Magdeburg, Germany},
  title        = {{Smart data adapter: A hybrid pattern-LLM approach}},
  doi          = {10.25673/123544},
  year         = {2026},
}