cs.AINov 6, 2026

Graph Visualizations in Prompts for Knowledge Graph Question Answering

Authors: Luiz do Valle Miranda, Andreas L. Opdahl, Grzegorz J. Nalepa

Organizations: Jagiellonian University, Kraków, Poland · University of Bergen, Bergen, Norway

Abstract

We study when and how multimodal input improves knowledge graph question answering (KGQA) in large vision--language models. Using a controlled evaluation over 1,500 WebQSP and CWQ questions and six VLMs within a fixed KGQA pipeline, we compare text-only prompting against text-plus-graph visualization at the per-question level and analyze performance changes as a function of reasoning complexity, model size, and image layout. Adding a graph image yields an average gain of 1.85 F1 points, driven by strong precision improvements on low-complexity questions (+4.65 F1). Mixed-effects and regression analyses show that these multimodal gains do not depend strongly on model scale, but are highly sensitive to graph layout: image-only settings sharply degrade performance, hierarchical Graphviz layouts outperform less organized renderings, and decomposing large subgraphs into separated paths yields the largest improvements. Taken together, the results indicate that visual prompting primarily aids KGQA by enhancing prediction precision in low-complexity contexts, provided that visual design respects cognitive and perceptual constraints. To optimize both accuracy and inference efficiency, we argue for adaptive visual prompting policies that selectively append diagrams to small, visually sparse subgraphs with well-structured layouts, avoiding unnecessary visual clutter and token overhead on complex queries. We conclude by relating these findings to a visual notation design theory, outlining how principled diagram encoding can guide future multimodal VLM prompting.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Question-Specific Knowledge Graphs for Efficient Visual Reasoning

    Sep 28, 2026Ting-Chih Chen, Emile van Krieken, Shujian Yu +1VLM ReasoningKnowledge-Based Visual Question Answering

  2. Q-CueGraph: Query-Conditioned Visual Evidence Graphs for Multimodal Reasoning

    Aug 5, 2026Pengcheng Pan, Xinfang ZhangVisual Question AnsweringEfficient VLM Inference

  3. Visual Graph Scaffolds for Structural Reasoning in Large Language Models

    Jun 1, 2026Runlin Lei, Xiaokui Xiao, Zhewei WeiLLM Reasoning with GraphsLLM Prompting