Skip to content
AI News HubLIVE
Original source2 min read

Graph Visualizations in Prompts for Knowledge Graph Question Answering

Summary

A controlled study evaluates when and how adding graph visualizations to prompts improves knowledge graph question answering in vision-language models, finding an average 1.85 F1 gain driven by low-complexity questions but highly sensitive to graph layout.

SourcearXiv AIAuthor: Luiz do Valle Miranda, Andreas L. Opdahl, Grzegorz J. Nalepa
Graph Visualizations in Prompts for Knowledge Graph Question Answering
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 6 Nov 2026]

Title:Graph Visualizations in Prompts for Knowledge Graph Question Answering

View a PDF of the paper titled Graph Visualizations in Prompts for Knowledge Graph Question Answering, by Luiz do Valle Miranda and 1 other authors

View PDF HTML (experimental)

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.

Comments: Accepted at AACL-IJCNLP conference

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2611.12938 [cs.AI]

(or arXiv:2611.12938v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2611.12938

arXiv-issued DOI via DataCite

Submission history

From: Luiz Do Valle Miranda [view email] [v1] Fri, 6 Nov 2026 14:55:29 UTC (5,675 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Graph Visualizations in Prompts for Knowledge Graph Question Answering, by Luiz do Valle Miranda and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.AI

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Adding a graph image to text prompts yields an average 1.85 F1 gain, with +4.65 F1 on low-complexity questions
  • Gains do not strongly depend on model scale but are highly sensitive to layout, with hierarchical Graphviz layouts performing best
  • Image-only settings sharply degrade performance; decomposing large subgraphs into separated paths gives the largest improvements
  • The authors advocate adaptive visual prompting that appends diagrams only to small, visually sparse subgraphs with well-structured layouts

Highlights and analysis are generated automatically and may contain errors. Check the original source.