@inproceedings{yoon-etal-2025-square,
    title = "{SQUARE}: Unsupervised Retrieval Adaptation via Synthetic Data",
    author = "Yoon, Jinsung  and
      Zeng, Junhao  and
      Arik, Sercan O",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.384/",
    doi = "10.18653/v1/2025.findings-emnlp.384",
    pages = "7283--7297",
    ISBN = "979-8-89176-335-7",
    abstract = "Pre-trained retrieval models often face challenges in zero-shot retrieval for knowledge-based question answering, as different tasks rely on different corpora. We introduce SQUARE (Synthetic QUery-based Adaptive REtrieval), a novel method for corpus-specific unsupervised retrieval customization. SQUARE leverages LLMs to generate grounded synthetic question-answer pairs from the corpus, which are then used to fine-tune the retriever. A filtering mechanism based on the synthetic answers is employed to ensure high quality of tuning data. Extensive experiments on various datasets demonstrate superior performance of SQUARE compared to zero-shot retrieval and other customization methods, highlighting the value of corpus adaptation for effective retrieval."
}