@inproceedings{tian-etal-2025-dutir831,
    title = "{DUTIR}831 at {S}em{E}val-2025 Task 5: A Multi-Stage {LLM} Approach to {GND} Subject Assignment for {TIBKAT} Records",
    author = "Tian, Yicen  and
      Yu, Erchen  and
      Wang, Yanan  and
      Li, Dailin  and
      Yao, Jiaqi  and
      Lin, Hongfei  and
      Zong, Linlin  and
      Xu, Bo",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.52/",
    pages = "363--372",
    ISBN = "979-8-89176-273-2",
    abstract = "This paper introduces DUTIR831{'}s approach to SemEval-2025 Task 5, which focuses on generating relevant subjects from the Integrated Authority File (GND) for tagging multilingual technical records in the TIBKAT database. To address challenges in understanding the hierarchical GND taxonomy and automating subject assignment, a three-stage approach is proposed: (1) a data synthesis stage that utilizes LLM to generate and selectively filter high-quality data, (2) a model training module that leverages LLMs and various training strategies to acquire GND knowledge and refine TIBKAT preferences, and (3) a subject terms completion mechanism consisting of multi-sampling ranking, subject terms extraction using a LLM, vector-based model retrieval, and various re-ranking strategies.The quantitative evaluation results show that our system is ranked 2nd in the all-subject datasets and 4th in the tib-core-subjects datasets. And the qualitative evaluation results show that the system is ranked 2nd in the tib-core-subjects datasets."
}