CoChat
Sign Up
Cited by 150Digital Media and Visual ArtInnovative Human-Technology InteractionDesign Education and Practice

Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation

Open access
Suh, Sangho, Chen, Meng, Min, Bryan, Li, Toby Jia-Jun, Xia, Haijun·2024·Proceedings of the CHI Conference on Human Factors in Computing Systems
DOI 10.1145/3613904.3642400
Open this paper in CoChat — free account

Abstract

Thanks to their generative capabilities, large language models (LLMs) have become an invaluable tool for creative processes. These models have the capacity to produce hundreds and thousands of visual and textual outputs, offering abundant inspiration for creative endeavors. But are we harnessing their full potential? We argue that current interaction paradigms fall short, guiding users towards rapid convergence on a limited set of ideas, rather than empowering them to explore the vast latent design space in generative models. To address this limitation, we propose a framework that facilitates the structured generation of design space in which users can seamlessly explore, evaluate, and synthesize a multitude of responses. We demonstrate the feasibility and usefulness of this framework through the design and development of an interactive system, Luminate, and a user study with 14 professional writers. Our work advances how we interact with LLMs for creative tasks, introducing a way to harness the creative potential of LLMs.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3613904.3642400

Cites

62 of 67 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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?

  • In the Academic context, translating support provides preliminary drafts or helps the user to restructure their ideas in a different form, but encourages the user to write and integrate ideas on their own.

    “Translating support provides preliminary drafts or helps the user to restructure their ideas in a different form (e.g., point form to prose), but encourages the user to write and integrate ideas on their own [21,122,124].”

    From Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process (2025) · cites this paper as [124]

    Section 4.2.4 (p. 11) describes a writer selecting AI-generated ideas and text, then editing them into a story draft; Section 6.1 (p. 12) likewise describes a participant editing and merging generated paragraphs. These passages support draft-making and user integration in creative writing, but do not establish translating support in an academic context, conversion from point form to prose, or an explicit encouragement to write ideas independently. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • Suh et al. highlighted that the current interaction paradigm with LLMs tends to converge on a limited set of ideas, potentially stifling creative exploration.

    “Suh et al. [58,59] highlighted that the current interaction paradigm with LLMs tends to converge on a limited set of ideas, potentially stifling creative exploration.”

    From Human Creativity in the Age of LLMs: Randomized Experiments on Divergent and Convergent Thinking (2025) · cites this paper as [58]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 9

  1. [9][9] Anastasia Bezerianos, Fanny Chevalier, Pierre Dragicevic, Niklas Elmqvist, and Jean-Daniel Fekete. 2010. Graphdice: A system for exploring multivariate social networks. In Computer graphics forum , Vol. 29. Wiley Online Library, 863-872. -
  2. [14][14] Stuart K Card, Jock Mackinlay, and Ben Shneiderman. 1999. Readings in information visualization: using vision to think . Morgan Kaufmann. https: //doi.org/10.5555/300679 - · DOI
  3. [16][16] Ruijia Cheng, Alison Smith-Renner, Ke Zhang, Joel R Tetreault, and Alejandro Jaimes. 2022. Mapping the design space of human-ai interaction in text summarization. arXiv preprint arXiv:2206.14863 (2022). https://doi.org/10.18653/v1/2022. naacl-main.33 - · DOI
  4. [33][33] Devamardeep Hayatpur, Daniel Wigdor, and Haijun Xia. 2023. CrossCode: Multilevel Visualization of Program Execution. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems . 1-13. https://doi.org/10.1145/ 3544548.3581390 -
  5. [34][34] Chris Heape. 2007. The Design Space: the design process as the construction, exploration and expansion of a conceptual space. (2007). https://www.semanticscholar.org/paper/The-Design-Space%3A-the-designprocess-as-the-and-of-Heape/40b912badea3b575a8f4bde95df4f83a4427ab78 -
  6. [53][53] Jeyakumar Muthukumarasamy and John T Stasko. 1995. Visualizing program executions on large data sets using semantic zooming. https://doi.org/10.5555/ 832277.834333 -
  7. [56][56] MCSchraefel, Max Wilson, Alistair Russell, and Daniel A Smith. 2006. mSpace: improving information access to multimedia domains with multimodal exploratory search. Commun. ACM 49, 4 (2006), 47-49. https://doi.org/10.1145/1121949. 1121980 - · DOI
  8. [59][59] Sangho Suh, Martinet Lee, Gracie Xia, et al. 2020. Coding strip: A pedagogical tool for teaching and learning programming concepts through comics. In 2020 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) . IEEE, 1-10. https://doi.org/10.1109/VL/HCC50065.2020.9127262 - · DOI
  9. [68][68] Daijin Yang, Yanpeng Zhou, Zhiyuan Zhang, Toby Jia-Jun Li, and Ray LC. 2022. AI as an Active Writer: Interaction strategies with generated text in humanAI collaborative fiction writing. In Joint Proceedings of the ACM IUI Workshops . https://hai-gen.github.io/2022/papers/paper-HAIGEN-YangDaijin.pdf -

Cited by

Sorted by citations

Related

Authors
Suh, S., Chen, M., Min, B., Li, T. J.-J., & Xia, H.
Affiliations
  • University of California San Diego (US)
  • University of Notre Dame (US)
ORCID
Venue
Proceedings of the CHI Conference on Human Factors in Computing Systems
Publisher
ACM
Published
2024-05-11
Pages
1-26
DOI
10.1145/3613904.3642400
OpenAlex
W4396832024
Cited by
148
References
60
Citations by year
2026: 62 · 2025: 76 · 2024: 10
FWCI
57.77
Type
conference paper
Language
en
Open access
Licence
Locations
  • CHI Conference on Human Factors in Computing Systems (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
Topics
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
  • Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
  • Physical Sciences › Engineering › Mechanical Engineering › Design Education and Practice
Keywords
large language models, human-AI co-creation, design space exploration, creative writing, structured generation, interactive system design, creative process

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