Knowledge Tree
knowledge fusion
Facts (24)
Sources
LLM-empowered knowledge graph construction: A survey - arXiv arxiv.org Oct 23, 2025 10 facts
referenceTraditional Knowledge Graph construction pipelines consist of three major components: ontology engineering, knowledge extraction, and knowledge fusion.
claimGraph-level models, such as those proposed by Liu et al. (2022), integrate semantic cues to enhance the robustness of entity alignment in Knowledge Fusion.
referenceClassical approaches to entity alignment in Knowledge Fusion relied on lexical and structural similarity measures, as reviewed in Zeng et al. (2021).
claimLarge Language Models are transforming Knowledge Graph construction by shifting the paradigm from rule-based and modular pipelines toward unified, adaptive, and generative frameworks across ontology engineering, knowledge extraction, and knowledge fusion.
claimMethodologies leveraging Large Language Models for knowledge fusion address challenges at two fundamental levels: constructing a unified and normalized knowledge skeleton at the schema layer, and integrating and aligning specific knowledge at the instance layer.
claimMulti-feature fusion strategies for Knowledge Fusion combine structural, attribute, and relational similarities to improve entity alignment, as demonstrated by Yang et al. (2022a).
referenceLinyao Yang, Chen Lv, Xiao Wang, Ji Qiao, Weiping Ding, Jun Zhang, and Fei-Yue Wang developed a collective entity alignment method for knowledge fusion of power grid dispatching knowledge graphs, published in the IEEE/CAA Journal of Automatica Sinica in 2022.
claimEmbedding-based techniques for entity alignment, which align entities within shared vector spaces, have improved scalability and automation in Knowledge Fusion, as surveyed by Zhu et al. (2024a).
referenceThe paper 'LLM-empowered knowledge graph construction: A survey' is organized into sections covering foundations of traditional KG construction (Section 2), LLM-enhanced ontology construction (Section 3), LLM-driven knowledge extraction (Section 4), LLM-powered knowledge fusion (Section 5), and future research directions including KG-based reasoning and dynamic knowledge memory (Section 6).
claimTraditional Knowledge Graph construction follows a three-layered pipeline comprising ontology engineering, knowledge extraction, and knowledge fusion.
Knowledge Graphs: Opportunities and Challenges - Springer Nature link.springer.com Apr 3, 2023 6 facts
claimThe challenges in developing knowledge graphs are categorized into the limitations of five topical technologies: knowledge graph embeddings, knowledge acquisition, knowledge graph completion, knowledge fusion, and knowledge reasoning.
referenceKnowledge fusion is a research direction focused on capturing knowledge from different sources and integrating it into a knowledge graph.
claimEntity alignment or ontology alignment is the primary method of knowledge fusion, aiming to match the same entity across multiple knowledge graphs.
claimSignificant technical challenges in knowledge graph development involve limitations in five representative technologies: knowledge graph embeddings, knowledge acquisition, knowledge graph completion, knowledge fusion, and knowledge reasoning.
claimKnowledge fusion is a necessary step for generating knowledge graphs that combines and integrates knowledge from different data sources.
claimEntity alignment is currently the primary method used for implementing knowledge fusion tasks.
Large Language Models Meet Knowledge Graphs for Question ... arxiv.org Sep 22, 2025 4 facts
claimComplex Question Answering (QA) involves question decomposition and knowledge fusion across multiple data modalities and sources, requiring complex knowledge reasoning to generate accurate answers.
claimThe combination of knowledge fusion, Retrieval-Augmented Generation (RAG), Chain-of-Thought (CoT) reasoning, and ranking-based refinement accelerates complex question decomposition for multi-hop Question Answering, enhances context understanding for conversational Question Answering, facilitates cross-modal interactions for multi-modal Question Answering, and improves the explainability of generated answers.
referenceKnowledge integration and fusion enhance language models by aligning knowledge graphs and text via local subgraph extraction and entity linking, then feeding the aligned data into a cross-model encoder to bidirectionally fuse text and knowledge graphs for joint training.
claimKnowledge graphs typically function as background knowledge when synthesizing large language models for complex question answering, with knowledge fusion and retrieval-augmented generation (RAG) serving as the primary technical paradigms.
The construction and refined extraction techniques of knowledge ... nature.com Feb 10, 2026 1 fact
procedureThe data processing framework for knowledge graphs described in the study 'The construction and refined extraction techniques of knowledge' standardizes data by unifying terminology, format, and semantics across sources, using cross-branch concept alignment, and applying domain constraints to promote consistency in downstream knowledge fusion.
[PDF] Large Language Models Meet Knowledge Graphs for Question ... aclanthology.org Nov 4, 2025 1 fact
claimGraphRAG and KG-RAG based question answering approaches incorporate modules including knowledge integration, knowledge fusion, and reasoning guidelines.
Knowledge Graphs: Opportunities and Challenges - arXiv arxiv.org Mar 24, 2023 1 fact
claimThe technical challenges in the field of knowledge graphs include knowledge graph embeddings, knowledge acquisition, knowledge graph completion, knowledge fusion, and knowledge reasoning.
Combining Knowledge Graphs and Large Language Models - arXiv arxiv.org Jul 9, 2024 1 fact
claimThe construction of knowledge graphs is difficult, costly, and time-consuming, requiring steps such as entity extraction, knowledge fusion, and coreference resolution.