@inproceedings{jin-etal-2026-king001,
    title = "king001 at {S}em{E}val-2026 Task 7: Cross-Language Cultural Everyday Knowledge {Q} A System Based on {RAG}",
    author = "Jin, Meizhi  and
      Meng, Zhichao  and
      Yin, Junqi  and
      Jiang, Lianxin  and
      Li, Jianyu",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.142/",
    pages = "1032--1049",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper describes our system used in the SemEval-2026 Task 7: Cross-Language Cultural Everyday Knowledge QA (track 1). Cultural knowledge typically exhibits significant regional specificity and is deeply rooted in particular linguistic conventions, posing severe challenges to general-purpose large language models (LLMs). We propose a retrieval-augmented generation (RAG) framework: this framework utilizes text-embedding-v4 as the retrieval core to precisely extract social knowledge and expression patterns from region-specific large-scale multilingual cultural knowledge bases, and drives the gpt-5.2-chat model to generate concise answers that are both logically factual and highly aligned with the target region{'}s cultural context. In the official evaluation, our system ranked first among all participating teams with a total score of 78.7672, fully demonstrating the method{'}s outstanding performance in cross-cultural accuracy and linguistic authenticity."
}