The Scenic Route to Deception: Dark Patterns and Explainability Pitfalls in Conversational Navigation

TL;DR

This paper examines the risks of manipulation and trust issues in AI-powered conversational navigation, proposing design strategies and a neuro-symbolic architecture to enhance transparency and safety.

Contribution

It introduces a framework for categorizing navigation risks and advocates for neuro-symbolic systems to improve explainability and trustworthiness.

Findings

Categorized navigation risks into intentional and unintentional harms.

Proposed seamful design strategies to mitigate manipulation and explainability issues.

Suggested neuro-symbolic architecture for verifiable and transparent navigation.

Abstract

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.