Exploring creativity in human-AI co-creation: a comparative study across design experience
Open accessThe DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Abstract
As generative artificial intelligence (GAI) becomes increasingly integrated into the design domain, research has begun to explore how it can be meaningfully incorporated into traditional design practices, fostering the development of more collaborative design processes. This study proposes a Human–AI Co-Creative Design Process (HAI-CDP) model and evaluates its impact on designers’ creativity through a comparative experimental design. The results indicate that the HAI-CDP substantially improves creative performance over the traditional design process. For novice designers, its primary value lies in facilitating idea generation, whereas for experienced designers, it contributes more to elevating the quality and refinement of creative outcomes. Although the Human–AI Co-Creative Design Process lowers the entry barrier to creative engagement, the findings also reaffirm that design experience remains a critical factor shaping creative output.
Overview
CoChat Summary
TL;DR
This study proposes a Human–AI Co-Creative Design Process (HAI-CDP) model, built from interviews with 13 professional designers and the Double Diamond framework, and tests it against a Traditional Creative Design Process (TCDP) in a 2 × 2 experiment with 42 designers. The HAI-CDP significantly improved creative performance on every measured dimension, but its benefits differed by experience: novices gained most in idea generation, while experienced designers gained most in quality and refinement.
Key findings
- HAI-CDP outperformed TCDP across all five creativity dimensions. For novices, significant gains appeared in creative support capability (t = 8.645, p < 0.001), quality (t = 13.974, p < 0.001), refinement (t = 19.481, p < 0.001), and number of ideas (t = 8.919, p < 0.001); for experienced designers, the largest gains were quality (t = 21.359, p < 0.001) and refinement (t = 21.855, p < 0.001), with novelty also significant (t = 17.426, p < 0.001).
- Experience effects persisted under HAI-CDP: experienced designers still scored significantly higher on novelty (t = 6.526, p < 0.001), quality (t = 6.145, p < 0.001), refinement (t = 13.099, p < 0.001), and number of ideas (t = 6.460, p < 0.001), while the experience gap in perceived creative support disappeared (t = −0.591, p > 0.05).
- Gap-reduction analysis showed HAI-CDP improved novices' creative support capability (Gap Reduction = +133.33%) but widened the experience gap in novelty (−55.09%), quality (−14.54%), and number of ideas (−78.95%).
- Two-way ANOVA found significant main effects of design process on all dimensions (e.g., Refinement F(1, 80) = 619, p < 0.001) and a significant process × experience interaction only for number of ideas generated (F(1, 80) = 5.56, p = 0.021); no significant interactions for novelty, quality, refinement, or creative support. Reliability was Cronbach's alpha = 0.878.
Methods
- Stage 1: semi-structured interviews with 13 professional designers (all with >3 years of project experience) in visual design and animation, analyzed via three-level coding, yielding four stages (concept definition, visual exploration, design development, implementation integration) and a Four-Diamond extension of the Double Diamond model.
- Stage 2: a 2 × 2 factorial experiment with 42 designers (21 novices — second-year animation/visual design undergraduates, mean age 19.67, SD = 0.73; 21 experienced — >3 years' experience, mean age 28.38, SD = 1.36). Each participant completed a 48-h online character design task ("Mechanical Beings of a Future World") under both TCDP and HAI-CDP, always in that order.
- Five dependent variables (perceived creative support capability, novelty, quality, refinement, number of ideas); novelty, quality, and refinement rated on a 5-point Likert scale by three blind expert raters (>10 years' experience), averaged; analyzed with paired-sample t-tests, independent-samples t-tests, and two-way ANOVA in SPSS 27.
Limitations
- Stated by the authors: the participant pool was limited to animation and visual design students and designers; the relatively small sample size may constrain generalizability; and the subjective nature of creative assessments may have influenced outcomes.
- Evident in the text: all participants completed TCDP before HAI-CDP, so order and carryover effects were not counterbalanced (the authors justify this as protecting the human-only baseline, but it remains a confound); the paper also notes a correction has been applied to the article.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 8 Not valid · 4 Not checked · 74 Own results and interpretations
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although the Human–AI Co-Creative Design Process lowers the entry barrier to creative engagement, the findings also reaffirm that design experience remains a critical factor shaping creative output.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For novice designers, its primary value lies in facilitating idea generation, whereas for experienced designers, it contributes more to elevating the quality and refinement of creative outcomes.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The interaction effect analysis revealed that the interaction between design process and designer experience was significant only in the dimension of Number of Ideas Generated (F(1, 80) = 5.56, p = 0.021)”
§ 4 Results > 4.3 Analysis of the interaction between design process and designer experience
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, in the dimension of Creative Support Capability, the main effect of experience was not significant (F(1, 80) = 0.755, p = 0.388)”
§ 4 Results > 4.3 Analysis of the interaction between design process and designer experience
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“During the concept definition stage, designers primarily relied on language-based generative tools such as ChatGPT, Claude AI, and Gemini to support task interpretation, keyword extraction, and the development of initial textual concepts.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
29 more claims
Create a free account to see all 86 claims and every source verdict.
- It may state two separate claims as one. 33
- Probably not a substantial claim. 28
Statistics recomputed
Every reported test result, recomputed from its test statistic and degrees of freedom. A result shows as not adding up only once an independent check has confirmed it.
- ConsistentF(1, 80) = 170reported p < .001 · recomputed p < .001
“F(1,80) = 170, p < .001”
- ConsistentF(1, 80) = 448reported p < .001 · recomputed p < .001
“F(1, 80) = 448, p < .001”
- ConsistentF(1, 80) = 377reported p < .001 · recomputed p < .001
“F(1, 80) = 377, p < .001”
- ConsistentF(1, 80) = 619reported p < .001 · recomputed p < .001
“F (1, 80) = 619, p < .001”
- ConsistentF(1, 80) = 178reported p < .001 · recomputed p < .001
“F(1, 80) = 178, p < .001”
10 more recomputed tests
Create a free account to see every test the Stats check recomputed.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ 6 Conclusion
“The Human–AI Co-Creative Design Process seems to narrow this gap, enabling novice designers to produce results closer to those of experienced designers.”
§ 4 Results > 4.2 Analysis of the impact of design experience on creativity
“However, in two key creative dimensions (Novelty and Quality) the gap widened, with Gap Reduction values of −55.09% and −14.54%, respectively. In the dimension of Number of Ideas Generated, the advantage of experienced designers was further amplified under the HAI-CDP condition, with a Gap Reduction of −78.95%.”
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ 4 Results > 4.3 Analysis of the interaction between design process and designer experience
“Novice designers showed a more substantial increase in the number of ideas produced, while the improvement among experienced designers was comparatively smaller.”
§ 4 Results > 4.2 Analysis of the impact of design experience on creativity
“In the dimension of Number of Ideas Generated, the advantage of experienced designers was further amplified under the HAI-CDP condition, with a Gap Reduction of −78.95%.”
Citations
Cites
The role of deliberate practice in the acquisition of expert performance
Ericsson, K. A., Krampe, R. T., & Tesch-Römer, C. (1993) · Psychological Review · doi:10.1037/0033-295x.100.3.363 · Cited by 9,564 · cited 2×
“According to Ericsson et al.’s (1993) theory of expertise, professional skills improve through goal-directed effort, regular feedback, and sustained training over time (Ericsson et al., 1993).”
What is coefficient alpha? An examination of theory and applications
Cortina, J. M. (1993) · Journal of Applied Psychology · doi:10.1037/0021-9010.78.1.98 · Cited by 8,810
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712 · cited 1×
“These models operate by progressively adding and removing noise from image data, enabling the generation of visually coherent and detail-rich imagery (Ho et al., 2020).”
The standard definition of creativity
Runco, M. A., & Jaeger, G. J. (2012) · Creativity Research Journal · doi:10.1080/10400419.2012.650092 · Cited by 3,895
Guidelines for Human-AI Interaction
Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., Suh, J., Iqbal, S., Bennett, P. N., Inkpen, K., et al. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300233 · Cited by 2,439
TVERSKY, B., MORRISON, J. B., & BETRANCOURT, M. (2002) · International Journal of Human-Computer Studies · doi:10.1006/ijhc.2002.1017 · Cited by 1,671 · cited 1×
“In addition, the quality of the final design output is often determined by the designer’s level of experience (Tversky et al., 2002).”
Non-normal data: Is ANOVA still a valid option?
Blanca, M., Alarcón, R., Arnau, J., Bono, R., & Bendayan, R. (2017) · Psicothema · doi:10.7334/psicothema2016.383 · Cited by 1,624 · cited 1×
“Given the balanced group sizes ( n = 21 per group) and prior findings that parametric tests are robust to moderate deviations from normality (Blanca Mena et al., 2017), the use of t-tests and ANOVA was deemed appropriate.”
Finetuned Language Models Are Zero-Shot Learners
Wei, J., Bosma, M., Zhao, V. Y., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., & Le, Q. V. (2021) · arXiv · doi:10.48550/arxiv.2109.01652 · Cited by 1,101 · cited 6×
“In the divergent phase, AI tools such as Midjourney and ChatGPT enable designers to quickly generate a large volume of ideas and conceptual directions, pushing the boundaries of creative exploration.”
InfluentialMetrics for measuring ideation effectiveness
Shah, J. J., Smith, S. M., & Vargas-Hernandez, N. (2003) · Design Studies · doi:10.1016/s0142-694x(02)00034-0 · Cited by 1,095
Shneiderman, B. (2022) · doi:10.1093/oso/9780192845290.001.0001 · Cited by 955
Simonton, D. K. (2003) · Psychological Bulletin · doi:10.1037/0033-2909.129.4.475 · Cited by 722 · cited 1×
“As a result, their work tends to be both more original and more complete in concept (Simonton, 2003).”
Expertise in design: an overview
Cross, N. (2004) · Design Studies · doi:10.1016/j.destud.2004.06.002 · Cited by 644 · cited 1×
“This early structuring allows them to gather relevant information efficiently and to shape a more focused direction for developing ideas and solutions (Cross, 2023; Cross, 2004).”
Longo, L., Brcic, M., Cabitza, F., Choi, J., Confalonieri, R., Ser, J. D., Guidotti, R., Hayashi, Y., Herrera, F., Holzinger, A., et al. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102301 · Cited by 626
AI super-powers: China, Silicon Valley and the new world order
Klingler-Vidra, R. (2019) · International Affairs · doi:10.1093/ia/iiz011 · Cited by 618
Sarkar, P., & Chakrabarti, A. (2011) · Design Studies · doi:10.1016/j.destud.2011.01.002 · Cited by 451
The importance of drawing in the mechanical design process
Ullman, D. G., Wood, S., & Craig, D. (1990) · Computers & Graphics · doi:10.1016/0097-8493(90)90037-x · Cited by 399 · cited 1×
“A critical step in this translation is the production of numerous conceptual sketches, which serve as the primary means of converting novel ideas into visual representations (Ullman et al., 1990).”
Creativity in Context: Update to The Social Psychology of Creativity
Amabile, T. M., Amabile, T. M., Collins, M. A., Conti, R., Phillips, E., Picariello, M., Ruscio, J., & Whitney, D. (2018) · doi:10.4324/9780429501234 · Cited by 399
The Effects of Generative AI on Design Fixation and Divergent Thinking
Wadinambiarachchi, S., Kelly, R. M., Pareek, S., Zhou, Q., & Velloso, E. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642919 · Cited by 320 · cited 1×
“Wadinambiarachchi et al. (2024) found that when designers rely too heavily on AI-generated outputs, they are more likely to experience design fixation and a reduction in divergent thinking (Wadinambiarachchi et al., 2024).”
Assessing the quality of ideas from prolific, early-stage product ideation
Kudrowitz, B. M., & Wallace, D. (2013) · Journal of Engineering Design · doi:10.1080/09544828.2012.676633 · Cited by 213
AI Creativity and the Human-AI Co-creation Model
Wu, Z., Ji, D., Yu, K., Zeng, X., Wu, D., & Shidujaman, M. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-78462-1_13 · Cited by 186 · cited 1×
“Wu et al. (2021) proposed a Human–AI co-creativity model that divides the design process into six stages: perception, reflection, expression, collaboration, construction, and testing (Wu et al., 2021).”
Creativity through design heuristics: A case study of expert product design
Yilmaz, S., & Seifert, C. M. (2011) · Design Studies · doi:10.1016/j.destud.2011.01.003 · Cited by 182
Understanding design ideation mechanisms through multilevel aligned empirical studies
Hernandez, N. V., Shah, J. J., & Smith, S. M. (2010) · Design Studies · doi:10.1016/j.destud.2010.04.001 · Cited by 151 · cited 1×
“Novelty refers to the degree an idea is novel or unexpected, while quality assesses the feasibility of the idea and how well it responds to design requirements (Hernandez et al., 2010; Shah et al., 2003).”
Yin, H., Zhang, Z., & Liu, Y. (2023) · Systems · doi:10.3390/systems11120566 · Cited by 131
Design Thinking: Understanding How Designers Think and Work
Cross, N. (2023) · Bloomsbury Publishing Plc eBooks · doi:10.5040/9781350305090 · Cited by 129 · cited 2×
“At this stage, designers are required to integrate all design elements and finalize the complete design output (Cross, 2023).”
The effect of AI-based inspiration on human design ideation
Kim, J., & Maher, M. L. (2023) · International Journal of Design Creativity and Innovation · doi:10.1080/21650349.2023.2167124 · Cited by 114
Something Old, Something New: Revisiting Guilford's Conception of Creative Problem Solving
Mumford, M. D. (2001) · Creativity Research Journal · doi:10.1207/s15326934crj1334_04 · Cited by 105 · cited 1×
“Psychological research suggests that creativity is a universal human trait, and that divergent thinking and convergent thinking are core components of the creative thinking process (Mumford, 2001).”
LLM enabled generative collaborative design in a mixed reality environment
Xu, S., Yao, W. F., Zheng, P., Zhang, J., & Yu, C. (2024) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2024.04.030 · Cited by 103 · cited 1×
“This framework suggests a clear trend: generative AI is gradually shifting from being a simple tool to becoming a creative partner (Xu et al., 2024).”
A study of the influence of visual imagery on graphic design ideation
Laing, S., & Masoodian, M. (2016) · Design Studies · doi:10.1016/j.destud.2016.04.002 · Cited by 88
Insights of genius: imagery and creativity in science and art
(1997) · Choice Reviews Online · doi:10.5860/choice.34-5046 · Cited by 56 · cited 1×
“Creative thinking is often described as an unconscious information processing activity through which individuals arrive at new insights—where inspiration strikes suddenly, like a flash of lightning (Miller, 2012).”
Human-Computer Collaborative Visual Design Creation Assisted by Artificial Intelligence
Huang, L., & Zheng, P. (2022) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3554735 · Cited by 48
Rethinking designer agency: A case study of co-creation between designers and AI
Guo, X., Xiao, Y., Wang, J., & Ji, T. (2023) · IASDR 2023: Life-Changing Design · doi:10.21606/iasdr.2023.478 · Cited by 47
Self-citationCamba, J. D., Kimbrough, M., & Kwon, E. (2018) · J of Design Research · doi:10.1504/jdr.2018.092810 · Cited by 26
Lv, Y. (2023) · IEEE Intelligent Transportation Systems Magazine · doi:10.1109/mits.2023.3295392 · Cited by 15 · cited 1×
“…such tools do more than streamline rendering tasks—they enable the direct visual articulation of abstract concepts, fostering greater freedom in ideation and promoting a more dynamic, iterative approach to form development and stylistic experimentation throughout the design process (Lv, 2023).”
The Research and Design of an AIGC Empowered Fashion Design Product
Wu, Z., Tang, R., Wang, G., Li, H., Yang, S., & Shidujaman, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-60449-2_28 · Cited by 11
The Relation between Design Expertise and the Quality of Design Idea
Alipour, L. (2021) · Iran University of Science & Technology · doi:10.22068/ijaup.31.1.585 · Cited by 2 · cited 1×
“Because of this, their design outcomes are often fragmented and lack internal consistency (Alipour, 2021).”
Lin, Y., & Liu, H. (2024) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-60913-8_18
Research works printed but not linked: 1
- 2005, The ‘double diamond’ design process model
Cited by
Dong, A., Li, P., Chen, Y., Gibson, S., Zhao, L., & He, M. (2026) · Sustainability · doi:10.3390/su18115313 · Cited by 9
Co-Designing Collaborative Generative AI Tools for Freelancers
Imteyaz, K., Muller, M. J., Flores-Saviaga, C., & Savage, S. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790280 · Cited by 8
Empowering the Future Workforce
Tiaraningrum, L., & Sekti, B. A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7153-5.ch004 · Cited by 3
Su, X., Liu, T.-L., Ye, Z., & Mei, Y.-X. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1800866 · Cited by 2
Londoño-Proaño, C. (2026) · Frontiers in Human Dynamics · doi:10.3389/fhumd.2026.1777511 · Cited by 4
Metadata
- Authors
- Wang, N., Kim, H., Peng, J., & Wang, J.
- Affiliations
- Hongik University (KR)
- Corresponding author
- Kim, Hyunsuk
- Venue
- Frontiers in Computer Science
- Publisher
- Frontiers Media SA
- Published
- 2025-09-30
- Volume
- 7
- ISSN
- 2624-9898 (ISSN-L)
- OpenAlex
- W4414677733
- Cited by
- 59
- References
- 32
- Citations by year
- 2026: 55 · 2025: 4
- FWCI
- 16.98
- Type
- journal article
- Language
- en
- Update notices
- correction (2026-02-09)
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Computer Science (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Engineering › Mechanical Engineering › Design Education and Practice
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Creativity in Education and Neuroscience
- Keywords
- human-AI co-creation, generative AI, design creativity, co-design, design experience, novice designers, idea generation, creative performance, design process model
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.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.