Don't Detect, Just Correct: Can LLMs Defuse Deceptive Patterns Directly?
Figure 1: We provided the LLM GPT-4o with the HTML source of UIs like the one on the left, a fictional ticket shop using several deceptive patterns to manipulate users into purchasing VIP tickets.Several iterations of simply prompting the LLM to "Make that less manipulative" (our minimal prompt) resulted in the fair design on the right.
Authors
- Paul Miles Preuschoff (ORCID: https://orcid.org/0000-0002-3545-1579)
- Jan Borchers (ORCID: https://orcid.org/0000-0003-1509-3257)
- René Schäfer (ORCID: https://orcid.org/0000-0002-0078-1412)
- S. R. Hahn
- Kevin Fiedler (ORCID: https://orcid.org/0009-0008-3644-1488)
- Rene Niewianda
Institutions
- RWTH Aachen University (DE)
Publication Details
- Published
- 2025-04-25
- DOI
- https://doi.org/10.1145/3706599.3719683
- Citations
- 1
- Primary Topic
- Imbalanced Data Classification Techniques
- Type
- article
- Field-Weighted Citation Impact
- 2.48