2 Search Results for "Jiang, Xinke"

Document
Research
DOI: 10.4230/TGDK.3.2.3
GraphRAG on Technical Documents - Impact of Knowledge Graph Schema

Authors: Henri Scaffidi, Melinda Hodkiewicz, Caitlin Woods, and Nicole Roocke

Published in: TGDK, Volume 3, Issue 2 (2025). Transactions on Graph Data and Knowledge, Volume 3, Issue 2

Abstract
Retrieval Augmented Generation (RAG) is seeing rapid adoption in industry to enable employees to query information captured in proprietary data for their organisation. In this work, we test the impact of domain-relevant knowledge graph schemas on the results of Microsoft’s GraphRAG pipeline. Our approach aims to address the poor quality of GraphRAG responses on technical reports rich in domain-specific terms. The use case involves technical reports about geology, chemistry and mineral processing published by the Minerals Research Institute of Western Australia (MRIWA). Four schemas are considered: a simple five-class minerals domain expert-developed schema, an expanded minerals domain schema, the Microsoft GraphRAG auto-generated schema, and a schema-less GraphRAG. These are compared to a conventional baseline RAG. Performance is evaluated using a scoring approach that accounts for the mix of correct, incorrect, additional, and missing content in RAG responses. The results show that the simple five-class minerals domain schema extracts approximately 10% more entities from the MRIWA reports than the other schema options. Additionally, both the five-class and the expanded eight-class minerals domain schemas produce the most factually correct answers and the fewest hallucinations. We attribute this to the minerals-specific schemas extracting more relevant, domain-specific information during the Indexing stage. As a result, the Query stage’s context window includes more high-value content. This contributes to the observed improvement in answer quality compared to the other pipelines. In contrast, pipelines with fewer domain-related entities in the KG retrieve less valuable information, leaving more room for irrelevant content in the context window. Baseline RAG responses were typically shorter, less complete, and contained more hallucinations compared to our GraphRAG pipelines. We provide a complete set of resources at https://github.com/nlp-tlp/GraphRAG-on-Minerals-Domain/tree/main. These resources include links to the MRIWA reports, a set of questions (from simple to challenging) along with domain-expert curated answers, schemas, and evaluations of the pipelines.
Cite as

Henri Scaffidi, Melinda Hodkiewicz, Caitlin Woods, and Nicole Roocke. GraphRAG on Technical Documents - Impact of Knowledge Graph Schema. In Transactions on Graph Data and Knowledge (TGDK), Volume 3, Issue 2, pp. 3:1-3:24, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@Article{scaffidi_et_al:TGDK.3.2.3,
  author =	{Scaffidi, Henri and Hodkiewicz, Melinda and Woods, Caitlin and Roocke, Nicole},
  title =	{{GraphRAG on Technical Documents - Impact of Knowledge Graph Schema}},
  journal =	{Transactions on Graph Data and Knowledge},
  pages =	{3:1--3:24},
  ISSN =	{2942-7517},
  year =	{2025},
  volume =	{3},
  number =	{2},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/TGDK.3.2.3},
  URN =		{urn:nbn:de:0030-drops-248131},
  doi =		{10.4230/TGDK.3.2.3},
  annote =	{Keywords: RAG, minerals, local search, global search, entity extraction, competency questions}
}
Document
Short Paper
DOI: 10.4230/LIPIcs.GIScience.2023.33
Uncertainty Quantification in the Road-Level Traffic Risk Prediction by Spatial-Temporal Zero-Inflated Negative Binomial Graph Neural Network(STZINB-GNN) (Short Paper)

Authors: Xiaowei Gao, James Haworth, Dingyi Zhuang, Huanfa Chen, and Xinke Jiang

Published in: LIPIcs, Volume 277, 12th International Conference on Geographic Information Science (GIScience 2023)

Abstract
Urban road-based risk prediction is a crucial yet challenging aspect of research in transportation safety. While most existing studies emphasize accurate prediction, they often overlook the importance of model uncertainty. In this paper, we introduce a novel Spatial-Temporal Zero-Inflated Negative Binomial Graph Neural Network (STZINB-GNN) for road-level traffic risk prediction, with a focus on uncertainty quantification. Our case study, conducted in the Lambeth borough of London, UK, demonstrates the superior performance of our approach in comparison to existing methods. Although the negative binomial distribution may not be the most suitable choice for handling real, non-binary risk levels, our work lays a solid foundation for future research exploring alternative distribution models or techniques. Ultimately, the STZINB-GNN contributes to enhanced transportation safety and data-driven decision-making in urban planning by providing a more accurate and reliable framework for road-level traffic risk prediction and uncertainty quantification.
Cite as

Xiaowei Gao, James Haworth, Dingyi Zhuang, Huanfa Chen, and Xinke Jiang. Uncertainty Quantification in the Road-Level Traffic Risk Prediction by Spatial-Temporal Zero-Inflated Negative Binomial Graph Neural Network(STZINB-GNN) (Short Paper). In 12th International Conference on Geographic Information Science (GIScience 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 277, pp. 33:1-33:6, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@InProceedings{gao_et_al:LIPIcs.GIScience.2023.33,
  author =	{Gao, Xiaowei and Haworth, James and Zhuang, Dingyi and Chen, Huanfa and Jiang, Xinke},
  title =	{{Uncertainty Quantification in the Road-Level Traffic Risk Prediction by Spatial-Temporal Zero-Inflated Negative Binomial Graph Neural Network(STZINB-GNN)}},
  booktitle =	{12th International Conference on Geographic Information Science (GIScience 2023)},
  pages =	{33:1--33:6},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-288-4},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{277},
  editor =	{Beecham, Roger and Long, Jed A. and Smith, Dianna and Zhao, Qunshan and Wise, Sarah},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.GIScience.2023.33},
  URN =		{urn:nbn:de:0030-drops-189286},
  doi =		{10.4230/LIPIcs.GIScience.2023.33},
  annote =	{Keywords: Traffic Risk Prediction, Uncertainty Quantification, Zero-Inflated Issues, Road Safety}
}
  • Refine by Type
  • 2 Document/PDF
  • 1 Document/HTML

  • Refine by Publication Year
  • 1 2025
  • 1 2023

  • Refine by Author
  • 1 Chen, Huanfa
  • 1 Gao, Xiaowei
  • 1 Haworth, James
  • 1 Hodkiewicz, Melinda
  • 1 Jiang, Xinke
  • Show More...

  • Refine by Series/Journal
  • 1 LIPIcs
  • 1 TGDK

  • Refine by Classification
  • 1 Information systems → Geographic information systems
  • 1 Information systems → Specialized information retrieval

  • Refine by Keyword
  • 1 RAG
  • 1 Road Safety
  • 1 Traffic Risk Prediction
  • 1 Uncertainty Quantification
  • 1 Zero-Inflated Issues
  • Show More...

Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact