The Scenic Route to Deception: Dark Patterns and Explainability Pitfalls in Conversational Navigation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917345007501312 |
|---|---|
| author | Ilyankou, Ilya Cavazzi, Stefano Haworth, James |
| author_facet | Ilyankou, Ilya Cavazzi, Stefano Haworth, James |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14586 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Scenic Route to Deception: Dark Patterns and Explainability Pitfalls in Conversational Navigation Ilyankou, Ilya Cavazzi, Stefano Haworth, James Human-Computer Interaction Artificial Intelligence Computers and Society 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. |
| title | The Scenic Route to Deception: Dark Patterns and Explainability Pitfalls in Conversational Navigation |
| topic | Human-Computer Interaction Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2603.14586 |