PopBlends: Strategies for Conceptual Blending with Large Language Models
Open accessAbstract
Pop culture is an important aspect of communication. On social media people often post pop culture reference images that connect an event, product or other entity to a pop culture domain. Creating these images is a creative challenge that requires finding a conceptual connection between the users’ topic and a pop culture domain. In cognitive theory, this task is called conceptual blending. We present a system called PopBlends that automatically suggests conceptual blends. The system explores three approaches that involve both traditional knowledge extraction methods and large language models. Our annotation study shows that all three methods provide connections with similar accuracy, but with very different characteristics. Our user study shows that people found twice as many blend suggestions as they did without the system, and with half the mental demand. We discuss the advantages of combining large language models with knowledge bases for supporting divergent and convergent thinking.
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.
Integrity signals
Registry
Cites
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.
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?
Providing stimuli that can ignite creative thinking in children aids them in detailing and refining their stories and helps them overcome artist's block.
“Second, it is crucial to provide stimuli that can ignite creative thinking in children, aiding them in the detailing and refinement of their stories; such stimuli can help children overcome artist's block [44, 71].”
From ChatScratch: An AI-Augmented System Toward Autonomous Visual Programming Learning for Children Aged 6-12 (2024) · cites this paper as [71]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 54 · Cited by 64
Research works printed but not linked: 9
- Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Pra- fulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jefrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877-1901. https://proceedings. neurips.cc/paper/2020/fle/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf
- Simon De Deyne, Danielle J Navarro, Amy Perfors, Marc Brysbaert, and Gert Storms. 2019. The "Small World of Words" English word association norms for over 12,000 cue words. Behavior research methods 51, 3 (2019), 987-1006.
- Simon De Deyne, Amy Perfors, and Daniel J Navarro. 2016. Predicting human similarity judgments with distributional models: The value of word associations.. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. The COLING 2016 Organizing Committee, Osaka, Japan, 1861-1870. https://aclanthology.org/C16-1175
- Kenton Lee, Luheng He, and Luke Zettlemoyer. 2018. Higher-Order Coreference Resolution with Coarse-to-Fine Inference. In North American Chapter of the Association for Computational Linguistics.
- Douglas Lenat. 1995. CYC: A Large-Scale Investment in Knowledge Infrastructure. Commun. ACM 38, 11 (November 1995), 33-38.
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jef Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111-3119.
- Cmara Pereira and Francisco. 2007. Creativity and Artifcial Intelligence: A Con- ceptual Blending Approach (1st ed.). Walter de Gruyter, USA.
- Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning. PMLR, 8821-8831.
- Juan Ramos et al. 2003. Using tf-idf to determine word relevance in document queries. In Proceedings of the frst instructional conference on machine learning, Vol. 242. Citeseer, 29-48.
- Authors
- Wang, S., Petridis, S., Kwon, T., Ma, X., & Chilton, L. B.
- Affiliations
- Columbia University (US)
- Hong Kong University of Science and Technology (HK)
- Venue
- Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2023-04-19
- Pages
- 1-19
- OpenAlex
- W4366548479
- Cited by
- 64
- References
- 54
- Citations by year
- 2026: 9 · 2025: 24 · 2024: 30 · 2023: 1
- FWCI
- 6.84
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Engineering › Mechanical Engineering › Design Education and Practice
- Keywords
- conceptual blending, pop culture references, large language models, knowledge base, knowledge extraction, divergent thinking, convergent thinking, cognitive load, user study
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
