{"type":"ScholarlyArticle","title":"How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback","authors":[{"name":"Manzong Huang","slug":"manzong-huang","given":"Manzong","family":"Huang","affiliation":""},{"name":"Chenyang Bu","slug":"chenyang-bu","given":"Chenyang","family":"Bu","affiliation":""},{"name":"Yi He","slug":"yi-he","given":"Yi","family":"He","affiliation":""},{"name":"Xindong Wu","slug":"xindong-wu","given":"Xindong","family":"Wu","affiliation":""}],"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. \r\nIn 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. \r\nExperiments 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.","doi":"10.24963/ijcai.2025/901","url":"https://ijcai.org/proceedings/2025/901","pdf":"https://ijcai.org/proceedings/2025/0901.pdf","markdown":"https://ijcai.org/proceedings/2025/901.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/901","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Natural Language Processing","track":"Main Track","number":901,"pages":{"first":8104,"last":8112},"keywords":["Natural Language Processing: NLP: Applications","Natural Language Processing: NLP: Question answering","Data Mining: DM: Knowledge graphs and knowledge base completion"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}