The Scenic Route to Deception: Dark Patterns and Explainability Pitfalls in Conversational Navigation
This addresses safety and transparency issues for users of AI-driven navigation systems, though it is incremental as it builds on existing explainability and design concepts.
The paper tackles the problem of manipulation and misplaced trust in conversational navigation systems using Generative AI, proposing a neuro-symbolic architecture to ground AI capabilities in verifiable algorithms and mitigate risks through seamful design strategies.
As pedestrian navigation increasingly experiments with Generative AI, and in particular Large Language Models, the nature of routing risks transforming from a verifiable geometric task into an opaque, persuasive dialogue. While conversational interfaces promise personalisation, they introduce risks of manipulation and misplaced trust. We categorise these risks using a 2x2 framework based on intent and origin, distinguishing between intentional manipulations (dark patterns) and unintended harms (explainability pitfalls). We propose seamful design strategies to mitigate these harms. We suggest that one robust way to operationalise trustworthy conversational navigation is through neuro-symbolic architecture, where verifiable pathfinding algorithms ground GenAI's persuasive capabilities, ensuring systems explain their limitations and incentives as clearly as they explain the route.