@inproceedings{lee-etal-2025-trag,
    title = "t{RAG}: Term-level Retrieval-Augmented Generation for Domain-Adaptive Retrieval",
    author = "Lee, Dohyeon  and
      Kim, Jongyoon  and
      Kim, Jihyuk  and
      Hwang, Seung-won  and
      Park, Joonsuk",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-long.334/",
    pages = "6566--6578",
    ISBN = "979-8-89176-189-6",
    abstract = "Neural retrieval models have emerged as an effective tool for information retrieval, but their performance suffers when there is a domain shift between training and test data distributions. Recent work aims to construct pseudo-training data for the target domain by generating domain-adapted pseudo-queries using large language models (LLMs). However, we identifies that LLMs exhibit a ``seen term bias'' where the generated pseudo-queries fail to include relevant ``unseen'' terms as expected for domain adaptation purposes. To address this limitation, we propose to improve the term recall of unseen query terms, by using term-level Retrieval-Augmented Generation (tRAG). Specifically, unlike existing document-level RAG, we propose to generate domain-specific keywords from all documents in the corpus, including those unseen in any individual document. To filter hallucination, generated keywords are retrieved and reranked, leveraging relevance feedback from both retrievers and LLMs. Experiments on the BEIR benchmark show tRAG significantly improves recall for unseen terms by 10.6{\%} and outperforms LLM and retrieval-augmented generation baselines on overall retrieval performance."
}