CoChat
Sign Up
PreprintCited by 13Data Visualization and AnalyticsMultimodal Machine Learning ApplicationsExplainable Artificial Intelligence (XAI)

The DOI matches its Crossref record; 59 of the 59 references it cites were found in a registry or an index.

Foundation Model Assisted Visual Analytics: Opportunities and Challenges

Open access
Hutchinson, Maeve, Jianu, Radu, Slingsby, Aidan, Madhyastha, Pranava·2025·Computers & Graphics
DOI 10.2139/ssrn.5114734
Open this paper in CoChat — free account

Abstract

We explore the integration of foundation models, such as large language models (LLMs) and multimodal LLMs (MLLMs), into visual analytics (VA) systems through intuitive natural language interactions. We survey current research directions in this emerging field, examining how foundation models have already been integrated into key visualisation-related processes in VA: visual mapping, the creation of data visualisations; visualisation observation, the process of generating a finding through visualisation; and visualisation manipulation, changing the viewport or highlighting areas of interest within a visualisation. We also highlight new possibilities that foundation models bring to VA, in particular, the opportunities to use MLLMs to interpret visualisations directly, to integrate multimodal interactions, and to provide guidance to users. We finally conclude with a vision of future VA systems as collaborative partners in analysis and address the prominent challenges in realising this vision through foundation models. Our discussions in this paper aim to guide future researchers working on foundation model assisted VA systems and help them navigate common obstacles when developing these systems.

Overview

Integrity signals

Registry

Crossref · 10.2139/ssrn.5114734

Cites

59 of 59 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Flagged first, then by citations

Show all 58 references

Research works printed but not linked: 4

  1. Wenhu Chen, Image from Yang et al. [45]). as direct manipulation, touch, or gesture-based inputs. These modalities allow users to express themselves more precisely, offering greater control and specificity when manipulating visualisations, Direct manipulation techniques which underlie WIMP (Windows, Icons, Menus, Pointer)
  2. 2005, Illuminating the Path: The Research and Development Agenda for Visual Analytics
  3. T Gao, 2015, Data-Tone: Managing Ambiguity in Natural Language Interfaces for Data Visualization, Proc. UIST, ACM, 489
  4. V Setlur, 2016, Eviza: A Natural Language Interface for Visual Analysis, Proc. UIST, ACM, 365

Cited by

Sorted by citations

Related

See all

Metadata

Authors
Hutchinson, M., Jianu, R., Slingsby, A., & Madhyastha, P.
Affiliations
City, University of London (GB)
Corresponding author
Hutchinson, Maeve
ORCID
Venue
Computers & Graphics
Publisher
Elsevier BV
Published
2025
Volume
130
Pages
104246-104246
ISSN
0097-8493 (ISSN-L)
DOI
10.2139/ssrn.5114734
OpenAlex
W4410544637
Cited by
13
References
58
Citations by year
2026: 7 · 2025: 6
FWCI
4.56
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Computers & Graphics (publishedVersion, cc-by)
  • SSRN Electronic Journal (acceptedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • City Research Online (City University London) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Topics
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Data Visualization and Analytics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
Keywords
foundation models, visual analytics, large language models, multimodal large language models, natural language interaction, visual mapping, multimodal interaction, user guidance, collaborative analysis

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review