Don't Detect, Just Correct: Can LLMs Defuse Deceptive Patterns Directly?
René Schäfer, Paul Miles Preuschoff, Rene Niewianda, Sophie Hahn, Kevin Fiedler, Jan Borchers · 2025
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.