ShortPathQA: A Dataset for Controllable Fusion of Large Language Models with Knowledge Graphs

Authors: Mikhail Salnikov, Andrey Sakhovskiy, Irina Nikishina, Aida Usmanova, Angelie Kraft, Cedric Möller, Debayan Banerjee, Junbo Huang, Longquan Jiang 0001, Rana Abdullah, Xi Yan 0001, Elena Tutubalina, Ricardo Usbeck, Alexander Panchenko

Year: 2025

Conference: NLDB 2025

Abstract: In this work, we release the Shortest Path subgraph Question Answering (ShortPathQA) dataset, the first dataset that provides textual questions with pre-computed relevant subgraphs retrieved from the Wikidata Knowledge Graph (KG), standardizing the evaluation framework for Knowledge Graph Question Answering (KGQA). For this purpose, we utilize the Mintaka dataset for both training and testing and additionally create a manual question-answering subset for testing. Our baseline experiments with both supervised approaches and unsupervised Large Language Model (LLM) inference indicate that even a simplified KGQA formulation with given KG subgraphs and candidate answers remains challenging. Our analysis has shown that LLMs are unable to correctly process and utilize graph data structures without detailed prompt engineering or model tuning. This limitation highlights the need for the creation of this dataset as a training ground for the development of methods that enable LLMs to work more effectively with graph data.

Show BibTeX
@inproceedings{DBLP:conf/nldb/SalnikovSNUKMBHJAYTUP25,
  author       = {Mikhail Salnikov and
                  Andrey Sakhovskiy and
                  Irina Nikishina and
                  Aida Usmanova and
                  Angelie Kraft and
                  Cedric M{\"{o}}ller and
                  Debayan Banerjee and
                  Junbo Huang and
                  Longquan Jiang and
                  Rana Abdullah and
                  Xi Yan and
                  Elena Tutubalina and
                  Ricardo Usbeck and
                  Alexander Panchenko},
  editor       = {Ryutaro Ichise},
  title        = {ShortPathQA: {A} Dataset for Controllable Fusion of Large Language
                  Models with Knowledge Graphs},
  booktitle    = {Natural Language Processing and Information Systems - 30th International
                  Conference on Applications of Natural Language to Information Systems,
                  {NLDB} 2025, Kanazawa, Japan, July 4-6, 2025, Proceedings, Part {I}},
  series       = {Lecture Notes in Computer Science},
  volume       = {15836},
  pages        = {95--110},
  publisher    = {Springer},
  year         = {2025},
  url          = {https://doi.org/10.1007/978-3-031-97141-9\_7},
  doi          = {10.1007/978-3-031-97141-9\_7},
  timestamp    = {Sat, 18 Jul 2026 13:05:48 +0200},
  biburl       = {https://dblp.org/rec/conf/nldb/SalnikovSNUKMBHJAYTUP25.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}