paper-with-me

Papers

Graphusion: A RAG Framework for Knowledge Graph Construction with a Global Perspective

2024-10-23 · Rui Yang, Boming Yang, Aosong Feng, Sixun Ouyang, Moritz Blum, Tianwei She, Yuang Jiang, Freddy Lecue, Jinghui Lu, Irene Li

Knowledge Graphs (KGs) are crucial in the field of artificial intelligence and are widely used in downstream tasks, such as question-answering (QA). The construction of KGs typically requires significant effort from domain experts. Large Language Models (LLMs) have recently been used for Knowledge Graph Construction (KGC). However, most existing approaches focus on a local perspective, extracting knowledge triplets from individual sentences or documents, missing a fusion process to combine the knowledge in a global KG. This work introduces Graphusion, a zero-shot KGC framework from free text. It contains three steps: in Step 1, we extract a list of seed entities using topic modeling to guide the final KG includes the most relevant entities; in Step 2, we conduct candidate triplet extraction using LLMs; in Step 3, we design the novel fusion module that provides a global view of the extracted knowledge, incorporating entity merging, conflict resolution, and novel triplet discovery. Results show that Graphusion achieves scores of 2.92 and 2.37 out of 3 for entity extraction and relation recognition, respectively. Moreover, we showcase how Graphusion could be applied to the Natural Language Processing (NLP) domain and validate it in an educational scenario. Specifically, we introduce TutorQA, a new expert-verified benchmark for QA, comprising six tasks and a total of 1,200 QA pairs. Using the Graphusion-constructed KG, we achieve a significant improvement on the benchmark, for example, a 9.2% accuracy improvement on sub-graph completion.

📄 PDF Abstract BibTeX arXiv:2410.17600

Code (1)

irenezihuili/graphusion 공식 구현

Tasks

graph constructionKnowledge GraphsQuestion AnsweringRAGTriplet

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Graphusion: Leveraging Large Language Models for Scientific Knowledge Graph Fusion and Construction in NLP Education

2024-07-15 · Rui Yang, Boming Yang, Sixun Ouyang, Tianwei She 외

Knowledge graphs (KGs) are crucial in the field of artificial intelligence and are widely applied in downstream tasks, such as enhancing Question Answering (QA) systems. The construction of KGs typically requires signifi…

graph constructionKnowledge GraphsLink PredictionQuestion Answering+1

STEM: Structure-Tracing Evidence Mining for Knowledge Graphs-Driven Retrieval-Augmented Generation

2026-04-24 · Peng Yu, En Xu, Bin Chen, Haibiao Chen 외 arxiv

Knowledge Graph-based Question Answering (KGQA) plays a pivotal role in complex reasoning tasks but remains constrained by two persistent challenges: the structural heterogeneity of Knowledge Graphs(KGs) often leads to s…

Question AnsweringKnowledge Graphs

RAKG:Document-level Retrieval Augmented Knowledge Graph Construction

2025-04-14 · Hairong Zhang, Jiaheng Si, Guohang Yan, Boyuan Qi 외

With the rise of knowledge graph based retrieval-augmented generation (RAG) techniques such as GraphRAG and Pike-RAG, the role of knowledge graphs in enhancing the reasoning capabilities of large language models (LLMs) h…

coreference-resolutionCoreference ResolutionEntity Disambiguationgraph construction+4

An Automatic Graph Construction Framework based on Large Language Models for Recommendation

2024-12-24 · Rong Shan, Jianghao Lin, Chenxu Zhu, Bo Chen 외

Graph neural networks (GNNs) have emerged as state-of-the-art methods to learn from graph-structured data for recommendation. However, most existing GNN-based recommendation methods focus on the optimization of model str…

graph constructionQuantizationWorld Knowledge

TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generation

2025-10-18 · Wenbiao Tao, Xinyuan Li, Yunshi Lan, Weining Qian arxiv

Retrieval-Augmented Generation enhances language models by retrieving external knowledge to support informed and grounded responses. However, traditional RAG methods rely on fragment-level retrieval, limiting their abili…

Information Extraction