Semantic Bundling: Interactive Node and Edge Bundling to Simplify Knowledge Graphs using Large Language Models
2026-08-04 • Human-Computer Interaction
Human-Computer Interaction
AI summaryⓘ
The authors present Semantic Bundling, a method to help people understand complex knowledge graphs made from text documents. They use large language models to group related parts of the graph into simpler super nodes and super edges, making it easier to see big-picture connections. The summaries remain linked to the original documents, ensuring the information is grounded in real data. They demonstrate this approach with examples from movie reviews and intelligence work, highlighting how it uncovers useful insights.
Knowledge GraphSemantic BundlingLarge Language ModelsGraph VisualizationSuper NodesSuper EdgesText MiningGenerative AIData SummarizationVisual Analytics
Authors
Adam Coscia, Zeyu Hua, Eric Krokos, Timothy Lin, Alex Endert
Abstract
We present Semantic Bundling, a visual analytics technique for making sense of text documents represented as knowledge graphs (KGs). Representing a document corpus as a KG makes relationships between entities explicit, making KGs useful both to analyze directly and in computational workflows including ML pipelines and generative AI backends. However, as KGs grow they become difficult to interpret and visualize for specific tasks (e.g., the ``hairball problem''), with the meaning of each relationship often buried in dense source text. Semantic Bundling uses large language models (LLMs) to support user-driven bundling of nodes and edges in a KG into higher-level graph structures: super nodes, which collapse and summarize a region of the graph, and super edges, which summarize the connection between two entities. Results are linked to underlying triples and source documents, grounding summaries in evidence. We implement Semantic Bundling in AgentK, an open-source system that builds a KG from text documents and maps graph interactions to bundling operations. Through use cases on movie reviews and an intelligence analysis scenario, we show how Semantic Bundling reveals new insights in document collections, and synthesize our findings into a discussion of emerging challenges and opportunities in knowledge graph sensemaking.