Knowledge Graph
Knowledge graphs (KGs) are structured representations of information, aiming to organize data into interconnected entities and relationships to facilitate knowledge discovery and reasoning. Current research heavily focuses on integrating KGs with large language models (LLMs) to enhance question answering, knowledge graph completion, and other knowledge-intensive tasks, often employing retrieval-augmented generation (RAG) and graph neural network architectures. This integration improves the accuracy and efficiency of various applications, ranging from legal article recommendation and medical diagnosis to supporting legislative processes and scholarly research. The resulting advancements have significant implications for diverse fields requiring complex information processing and reasoning.
Papers
From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems
Ali Mohammadjafari, Anthony S. Maida, Raju Gottumukkala
Replacing Paths with Connection-Biased Attention for Knowledge Graph Completion
Sharmishtha Dutta, Alex Gittens, Mohammed J. Zaki, Charu C. Aggarwal
Conversational Exploratory Search of Scholarly Publications Using Knowledge Graphs
Phillip Schneider, Florian Matthes
GUNDAM: Aligning Large Language Models with Graph Understanding
Sheng Ouyang, Yulan Hu, Ge Chen, Yong Liu
Customized Information and Domain-centric Knowledge Graph Construction with Large Language Models
Frank Wawrzik, Matthias Plaue, Savan Vekariya, Christoph Grimm
Knowledge Graph Embedding by Normalizing Flows
Changyi Xiao, Xiangnan He, Yixin Cao
RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge Graph
Linxi Wei, Guorui Xiao, Magdalena Balazinska
SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs
Hanzhu Chen, Xu Shen, Qitan Lv, Jie Wang, Xiaoqi Ni, Jieping Ye