@inproceedings{pinto-etal-2025-exploring,
    title = "Exploring Medium-Sized {LLM}s for Knowledge Base Construction",
    author = "Pinto, Tom{\'a}s Cerveira Da Cruz  and
      Oliveira, Hugo Gon{\c{c}}alo  and
      Fleger, Chris-Bennet",
    editor = "Alam, Mehwish  and
      Tchechmedjiev, Andon  and
      Gracia, Jorge  and
      Gromann, Dagmar  and
      di Buono, Maria Pia  and
      Monti, Johanna  and
      Ionov, Maxim",
    booktitle = "Proceedings of the 5th Conference on Language, Data and Knowledge",
    month = sep,
    year = "2025",
    address = "Naples, Italy",
    publisher = "Unior Press",
    url = "https://preview.aclanthology.org/ldl-25-ingestion/2025.ldk-1.23/",
    pages = "221--232",
    ISBN = "978-88-6719-333-2",
    abstract = "19 Knowledge base construction (KBC) is one of the great challenges in Natural Language Processing (NLP) and of fundamental importance to the growth of the Semantic Web. Large Language Models (LLMs) may be useful for extracting structured knowledge, including subject-predicate-object triples. We tackle the LM-KBC 2023 Challenge by leveraging LLMs for KBC, utilizing its dataset and benchmarking our results against challenge participants. Prompt engineering and ensemble strategies are tested for object prediction with pretrained LLMs in the 0.5-2B parameter range, which is between the limits of tracks 1 and 2 of the challenge.Selected models are assessed in zero-shot and few-shot learning approaches when predicting the objects of 21 relations. Results demonstrate that instruction-tuned LLMs outperform generative baselines by up to four times, with relation-adapted prompts playing a crucial role in performance. The ensemble approach further enhances triple extraction, with a relation-based selection strategy achieving the highest F1 score. These findings highlight the potential of medium-sized LLMs and prompt engineering methods for efficient KBC."
}