How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback

Huang, Manzong; Bu, Chenyang; He, Yi; Wu, Xindong

doi:10.24963/ijcai.2025/901

How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback

Manzong Huang, Chenyang Bu, Yi He, Xindong Wu

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 8104-8112.

https://doi.org/10.24963/ijcai.2025/901

Keywords

Natural Language Processing: NLP: Applications
Natural Language Processing: NLP: Question answering
Data Mining: DM: Knowledge graphs and knowledge base completion

Abstract

Knowledge Graph (KG)-augmented Large Language Models (LLMs) have recently propelled significant advances in complex reasoning tasks, thanks to their broad domain knowledge and contextual awareness. Unfortunately, current methods often assume KGs to be complete, which is impractical given the inherent limitations of KG construction and the potential loss of contextual cues when converting unstructured text into entity-relation triples.

In response, this paper proposes the Triple Context Restoration and Query-driven Feedback (TCR-QF) framework, which reconstructs the textual context underlying each triple to mitigate information loss, while dynamically refining the KG structure by iteratively incorporating query-relevant missing knowledge.

Experiments on five benchmark question-answering datasets substantiate the effectiveness of TCR-QF in KG and LLM integration, where itachieves a 29.1% improvement in Exact Match and a 15.5% improvement in F1 over its state-of-the-art GraphRAG competitors. The code is publicly available at https://github.com/HFUT-DMiC-Lab/TCR-QF.git.

Manzong Huang, Chenyang Bu, Yi He, and Xindong Wu. 2025. How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 8104–8112. https://doi.org/10.24963/ijcai.2025/901

@inproceedings{ijcai2025p901,
  title     = {How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback},
  author    = {Huang, Manzong and Bu, Chenyang and He, Yi and Wu, Xindong},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {8104--8112},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/901},
  url       = {https://doi.org/10.24963/ijcai.2025/901},
}

TY  - CPAPER
TI  - How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback
AU  - Huang, Manzong
AU  - Bu, Chenyang
AU  - He, Yi
AU  - Wu, Xindong
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 8104
EP  - 8112
DO  - 10.24963/ijcai.2025/901
UR  - https://doi.org/10.24963/ijcai.2025/901
ER  -