Generative Pre-Trained Transformer for Design Concept Generation: An Exploration
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
Novel concepts are essential for design innovation and can be generated with the aid of data stimuli and computers. However, current generative design algorithms focus on diagrammatic or spatial concepts that are either too abstract to understand or too detailed for early phase design exploration. This paper explores the uses of generative pre-trained transformers (GPT) for natural language design concept generation. Our experiments involve the use of GPT-2 and GPT-3 for different creative reasonings in design tasks. Both show reasonably good performance for verbal design concept generation.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
On the difficulty of training recurrent neural networks
Pascanu, R., Mikolov, T., & Bengio, Y. (2012) · arXiv · doi:10.48550/arxiv.1211.5063 · Cited by 4,310
Gatt, A., & Krahmer, E. (2018) · Journal of Artificial Intelligence Research · doi:10.1613/jair.5477 · Cited by 776 · cited 2×
“According to Gatt and Krahmer [2018], depending on the input, there are two major instances of NLG: text-to-text and data-to-text generation.”
BackgroundInfluential
Cited by
Yenduri, G., Ramalingam, M., Selvi, G. C., Supriya, Y., Srivastava, G., Maddikunta, P. K. R., Raj, G. D., Jhaveri, R. H., Prabadevi, B., Wang, W., et al. (2024) · IEEE Access · doi:10.1109/access.2024.3389497 · Cited by 596
Ding, Z., Srinivasan, A., Macneil, S., & Chan, J. (2023) · Creativity and Cognition · doi:10.1145/3591196.3593516 · Cited by 35
“More broadly, our results add to prior work on the analogical reasoning capacities of LLMs, extending from simpler analogy word problems [5, 8, 73] to more complex cross-domain analogical outputs, and extending prior proofs-ofconcept [5, 73, 76] with systematic testing of analogical outputs in the context of creative…”
BackgroundResultInfluentialIdeationWeb: Tracking the Evolution of Design Ideas in Human-AI Co-Creation
Shen, H., Shen, L., Wu, W., & Zhang, K. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713375 · Cited by 24
“Currently, generative artifcial intelligence (GenAI), powered by LLMs, has been widely applied in multiple felds [26, 43], particularly showcasing signifcant potential in enhancing conceptual design [61, 73, 120].”
Mapping the Design Space of Interactions in Human-AI Text Co-creation Tasks
Ding, Z., & Chan, J. (2023) · arXiv · doi:10.48550/arxiv.2303.06430 · Cited by 9
“By creative, we mean outputs that are both novel and useful [22, 23], including generating analogies / metaphors / analogous design concepts [2, 16, 26, 29], slogans [8] and inspirations for tweetorials (short technical explanations on Twitter) [14].”
BackgroundA Field Test of Popular Chatbots’ Responses To Questions Concerning Negative Body Image
An, R., Byron, C. W., Chen, C., & Xiang, X. (2023) · Health Behavior Research · doi:10.4148/2572-1836.1164 · Cited by 6
Metadata
- Authors
- Zhu, Q., & Luo, J.
- Venue
- Proceedings of the Design Society
- Publisher
- Cambridge University Press (CUP)
- Published
- 2022-05
- Volume
- 2
- Pages
- 1825-1834
- ISSN
- 2732-527X (ISSN-L)
- OpenAlex
- W3213472637
- Cited by
- 101
- References
- 3
- FWCI
- 7.80
- Type
- journal article
- Language
- en
- Open access
- hybrid
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Generative Pre-Trained Transformer for Design Concept Generation: An Exploration. https://app.cochat.ai/papers/10.1017/pds.2022.185
- The paper
- Zhu, Q., & Luo, J. (2022). Generative Pre-Trained Transformer for Design Concept Generation: An Exploration. Proceedings of the Design Society. https://doi.org/10.1017/pds.2022.185
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.