@inproceedings{son-etal-2024-multi,
    title = "Multi-hop Database Reasoning with Virtual Knowledge Graph",
    author = "Son, Juhee  and
      Seonwoo, Yeon  and
      Yoon, Seunghyun  and
      Thorne, James  and
      Oh, Alice",
    editor = "Biswas, Russa  and
      Kaffee, Lucie-Aim{\'e}e  and
      Agarwal, Oshin  and
      Minervini, Pasquale  and
      Singh, Sameer  and
      de Melo, Gerard",
    booktitle = "Proceedings of the 1st Workshop on Knowledge Graphs and Large Language Models (KaLLM 2024)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.kallm-1.1",
    doi = "10.18653/v1/2024.kallm-1.1",
    pages = "1--11",
    abstract = "Application of LLM to database queries on natural language sentences has demonstrated impressive results in both single and multi-hop scenarios.In the existing methodologies, the requirement to re-encode query vectors at each stage for processing multi-hop queries presents a significant bottleneck to the inference speed.This paper proposes VKGFR (Virtual Knowledge Graph based Fact Retriever) that leverages large language models to extract representations corresponding to a sentence{'}s knowledge graph, significantly enhancing inference speed for multi-hop reasoning without performance loss.Given that both the queries and natural language database sentences can be structured as a knowledge graph, we suggest extracting a Virtual Knowledge Graph (VKG) representation from sentences with LLM.Over the pre-constructed VKG, our VKGFR conducts retrieval with a tiny model structure, showing performance improvements with higher computational efficiency. We evaluate VKGFR on the WikiNLDB and MetaQA dataset, designed for multi-hop database reasoning over text. The results indicate 13x faster inference speed on the WikiNLDB dataset without performance loss.",
}