@inproceedings{min-etal-2025-unihgkr,
    title = "{U}ni{HGKR}: Unified Instruction-aware Heterogeneous Knowledge Retrievers",
    author = "Min, Dehai  and
      Xu, Zhiyang  and
      Qi, Guilin  and
      Huang, Lifu  and
      You, Chenyu",
    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.234/",
    pages = "4577--4594",
    ISBN = "979-8-89176-189-6",
    abstract = "Existing information retrieval (IR) models often assume a homogeneous structure for knowledge sources and user queries, limiting their applicability in real-world settings where retrieval is inherently heterogeneous and diverse. In this paper, we introduce UniHGKR, a unified instruction-aware heterogeneous knowledge retriever that (1) builds a unified retrieval space for heterogeneous knowledge and (2) follows diverse user instructions to retrieve knowledge in specified types. UniHGKR consists of three principal stages, including heterogeneous self-supervised pretraining, text-anchored embedding alignment, and instruction-aware retriever fine-tuning, enabling it to generalize across varied retrieval contexts. This framework is highly scalable, with a BERT-based version and a UniHGKR-7B version trained on large language models. Also, we introduce CompMix-IR, the first native heterogeneous knowledge retrieval benchmark. It includes two retrieval scenarios with various instructions, over 9,400 question answer (QA) pairs, and a corpus of 10 million entries, covering four different types of data. Extensive experiments show that UniHGKR consistently outperform state-of-the-art methods on CompMix-IR, achieving up to 6.36{\%} and 54.23{\%} relative improvements in two scenarios, respectively. Finally, by equipping our retriever for open-domain heterogeneous QA systems, we achieve a new state-of-the-art result on the popular ConvMix task, with an absolute improvement of up to 5.90 points."
}