@inproceedings{bolucu-etal-2026-using,
    title = "Using a Human-{AI} Teaming Approach to Create and Curate Scientific Datasets with the {S}ci{L}ire System",
    author = {B{\"o}l{\"u}c{\"u}, Necva  and
      Irons, Jessica  and
      Lee, Changhyun  and
      Jin, Brian  and
      Rybinski, Maciej  and
      Yang, Huichen  and
      Duenser, Andreas  and
      Wan, Stephen},
    editor = "Croce, Danilo  and
      Leidner, Jochen  and
      Moosavi, Nafise Sadat",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = mar,
    year = "2026",
    address = "Rabat, Marocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-demo.30/",
    pages = "428--444",
    ISBN = "979-8-89176-382-1",
    abstract = "The rapid growth of scientific literature has made manual extraction of structured knowledge increasingly impractical. To address this challenge, we introduce SCILIRE, a system for creating datasets from scientific literature. SCILIRE has been designed around Human-AI teaming principles centred on workflows for verifying and curating data. It facilitates an iterative workflow in which researchers can review and correct AI outputs. Furthermore, this interaction is used as a feedback signal to improve future LLM-based inference. We evaluate our design using a combination of intrinsic benchmarking outcomes together with real-world case studies across multiple domains. The results demonstrate that SCILIRE improves extraction fidelity and facilitates efficient dataset creation."
}