Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 13

The DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.

"Create a Fear of Missing Out" - ChatGPT Implements Unsolicited Deceptive Designs in Generated Websites Without Warning

Krauß, Veronika, McGill, Mark, Kosch, Thomas, Thiel, Yolanda Maira, Schön, Dominik, Gugenheimer, Jan·2025·Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems
DOI 10.1145/3706598.3713083
Open this paper in CoChat — free account

Abstract

With the recent advancements in Large Language Models (LLMs), web developers increasingly apply their code-generation capabilities to website design. However, since these models are trained on existing designerly knowledge, they may inadvertently replicate bad or even illegal practices, especially deceptive designs (DD). This paper examines whether users can accidentally create DD for a fictitious webshop using GPT-4. We recruited 20 participants, asking them to use ChatGPT to generate functionalities (product overview or checkout) and then modify these using neutral prompts to meet a business goal (e.g., "increase the likelihood of us selling our product"). We found that all 20 generated websites contained at least one DD pattern (mean: 5, max: 9), with GPT-4 providing no warnings. When reflecting on the designs, only 4 participants expressed concerns, while most considered the outcomes satisfactory and not morally problematic, despite the potential ethical and legal implications for end-users and those adopting ChatGPT's recommendations

Overview

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 · 10.1145/3706598.3713083

Cites

40 of 40 references verified0 citation errors · 0 not checkable

Statistics

Figures

Image 1
CC-BY-SA · From the PDF
Image 2
CC-BY-SA · From the PDF
Table 1. Our participants' demographics; the experience levels (Exp.) are self-reported values of the five categories Novice, Advanced (Adv.) Beginner, Competent, Proficient, Expert
Table 1. Our participants' demographics; the experience levels (Exp.) are self-reported values of the five categories Novice, Advanced (Adv.) Beginner, Competent, Proficient, ExpertCC-BY-SA · From the PDF
Image 4
CC-BY-SA · From the PDF
Image 5
CC-BY-SA · From the PDF
Fig. 5 Lvl1 (left) and Lvl3 (right) versions of the the shoe shop's website. The HTML files were created in dataset 130:product. The patterns contained in Lvl3 are added as labels.
Fig. 5 Lvl1 (left) and Lvl3 (right) versions of the the shoe shop's website. The HTML files were created in dataset 130:product. The patterns contained in Lvl3 are added as labels.CC-BY-SA · From the PDF
Fig. 6 Bar charts depicting the open questions regarding 1) participant satisfaction, 2) creator of the website, 3) responsibility, and 4) morality of the resulting artifact. In 2) and 3), some answers were coded with more than one code, e.g., if a participant perceived both, the programmer and ChatGPT as the creator of the webpage in Subfigure 2. Therefore, in some of the bar charts, the total number of codes exceeds the total number of datasets (n=20).
Fig. 6 Bar charts depicting the open questions regarding 1) participant satisfaction, 2) creator of the website, 3) responsibility, and 4) morality of the resulting artifact. In 2) and 3), some answers were coded with more than one code, e.g., if a participant perceived both, the programmer and ChatGPT as the creator of the webpage in Subfigure 2. Therefore, in some of the bar charts, the total number of codes exceeds the total number of datasets (n=20).CC-BY-SA · From the PDF
Image 8
CC-BY-SA · From the PDF

Verification

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?

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

Show all 40 references

Research works printed but not linked: 12

  1. Anthropic. 2024. Introducing Claude Sonnet 3.5. Antrhopic. https://www.anthropic.com/news/claude-3-5-sonnet
  2. Evan Bailyn. 2024. Top Generative AI Chatbots by Market Share – September 2024. First Page Sage. https://firstpagesage.com/reports/top-generative-ai-chatbots/
  3. Harry Brignull. 2011. Dark Patterns: Deception vs. Honesty in UI Design. Interaction Design, Usability. https://alistapart.com/article/dark-patterns-deception-vs-honesty-in-ui-design/
  4. Harry Brignull. 2023. Deceptive Patterns: Exposing the Tricks Tech Companies Use to Control You. Harry Brignull, USA. https://books.google.de/books?id=PysW0AEACAAJ
  5. Colin M. Gray Thomas Mildner and Nataliia Bielova. 2023. Temporal Analysis of Dark Patterns: A Case Study of a User’s Odyssey to Conquer Prime Membership Cancellation through the "Iliad Flow". arxiv:https://arXiv.org/abs/2309.09635 [cs.HC] https://arxiv.org/abs/2309.09635 · arXiv
  6. Lujain Ibrahim Luc Rocher and Ana Valdivia. 2024. Characterizing and modeling harms from interactions with design patterns in AI interfaces. arxiv:https://arXiv.org/abs/2404.11370 [cs.HC] https://arxiv.org/abs/2404.11370 · arXiv
  7. Thomas Kosch and Sebastian Feger. 2024. Risk or Chance? Large Language Models and Reproducibility in Human-Computer Interaction Research. arxiv:https://arXiv.org/abs/2404.15782 [cs.HC] https://arxiv.org/abs/2404.15782 · arXiv
  8. Zhiming Li Yushi Cao Xiufeng Xu Junzhe Jiang Xu Liu Yon Shin Teo Shang wei Lin and Yang Liu. 2024. LLMs for Relational Reasoning: How Far are We? arxiv:https://arXiv.org/abs/2401.09042 [cs.AI] https://arxiv.org/abs/2401.09042 · arXiv
  9. Yi Liu Gelei Deng Zhengzi Xu Yuekang Li Yaowen Zheng Ying Zhang Lida Zhao Tianwei Zhang Kailong Wang and Yang Liu. 2024. Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study. arxiv:https://arXiv.org/abs/2305.13860 [cs.SE] https://arxiv.org/abs/2305.13860 · arXiv
  10. Arvind Narayanan Arunesh Mathur Marshini Chetty and Mihir Kshirsagar. 2020. Dark Patterns: Past Present and Future: The evolution of tricky user interfaces. Queue 18 2 (May 2020) 67–92. 10.1145/3400899.3400901 · DOI
  11. Proton Technologies AG. 2024. General Data Protection Regualtion (GDPR) Compliance Guidelines. Proton Technologies AG. https://gdpr.eu
  12. Robert Wolfe and Alexis Hiniker. 2024. Expertise Fog on the GPT Store: Deceptive Design Patterns in User-Facing Generative AI. In Mobilizing Research and Regulatory Action on Dark Patterns and Deceptive Design Practices Workshop at CHI Conference on Human Factors in Computing Systems. Honolulu, USA, 13 pages.

Cited by

Metadata

Authors
Krauß, V., McGill, M., Kosch, T., Thiel, Y. M., Schön, D., & Gugenheimer, J.
Affiliations
  • Technical University of Darmstadt, Darmstadt, Germany
  • School of Computing Science, University of Glasgow, Glasgow, Lanarkshire, United Kingdom
  • Humboldt University of Berlin, Berlin, Germany
ORCID
Venue
Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems
Publisher
ACM
Published
2025-04-25
Pages
1-20
DOI
10.1145/3706598.3713083
Cited by
13
References
40
Licence
www.acm.org/publications/policies/copyright_policy#Background (vor)
Funders
  • UK Research and Innovation (UKRI) (EP/Z000068/1)
  • German Research Foundation (DFG) (Project-ID 414984028)
  • National Research Center for Applied Cybersecurity ATHENE (XR-GUARD)

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

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.