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

• URL: http://arxiv.org/abs/2603.14586v1
• Date: Sun, 15 Mar 2026 20:10:00 GMT
• Title: The Scenic Route to Deception: Dark Patterns and Explainability Pitfalls in Conversational Navigation
• Abstract summary: We argue that conversational interfaces introduce risks of manipulation and misplaced trust.<n>We categorise these risks using a 2x2 framework based on intent and origin.<n>We suggest that one robust way to operationalise trustworthy conversational navigation is through neuro-symbolic architecture.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• "Why This Avoidance Maneuver?" Contrastive Explanations in Human-Supervised Maritime Autonomous Navigation [6.365194490730867]
  This paper explores how to explain causal logic behind avoidance maneuvers in a selective, understandable manner for supervisors with a nautical background.<n>We propose a method for generating contrastive explanations, which provide human-centric insights.<n>An exploratory user study with four experienced marine officers suggests that contrastive explanations support the understanding of the system's objectives.
  arXiv  Detail & Related papers  (2026-04-09T09:37:43Z)
• DSCD-Nav: Dual-Stance Cooperative Debate for Object Navigation [63.439158093945956]
  We propose Dual-Stance Cooperative Debate Navigation (DSCD-Nav) to replace one-shot scoring with stance-based cross-checking and evidence-aware arbitration.<n> Experiments on HM3Dv1, HM3Dv2, and MP3D demonstrate consistent improvements in success and path efficiency while reducing exploration redundancy.
  arXiv  Detail & Related papers  (2026-01-29T08:47:55Z)
• Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning [18.725403690215508]
  We highlight the risks related to overreliance and susceptibility to adversarial manipulation of "intrinsically" interpretable models by design.<n> Fooling the model's reasoning by exploiting its use of latent prototypes manifests the inherent uninterpretability of deep neural networks.<n>The reported limitations of part-prototype networks put their trustworthiness and applicability into question, motivating further work on the robustness and alignment of (deep) interpretable models.
  arXiv  Detail & Related papers  (2025-03-11T17:24:33Z)
• Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions [50.40122190627256]
  We introduce POATE, a novel jailbreak technique that harnesses contrastive reasoning to provoke unethical responses.<n>PoATE crafts semantically opposing intents and integrates them with adversarial templates, steering models toward harmful outputs with remarkable subtlety.<n>To counter this, we propose Intent-Aware CoT and Reverse Thinking CoT, which decompose queries to detect malicious intent and reason in reverse to evaluate and reject harmful responses.
  arXiv  Detail & Related papers  (2025-01-03T15:40:03Z)
• Manipulating Neural Path Planners via Slight Perturbations [2.7624021966289605]
  Data-driven neural path planners are attracting increasing interest in the robotics community. Their neural network components typically come as black boxes, obscuring their underlying decision-making processes. We propose a novel approach to specify and inject a range of hidden malicious behaviors, known as backdoors, into neural path planners.
  arXiv  Detail & Related papers  (2024-03-27T04:56:48Z)
• Instruct2Attack: Language-Guided Semantic Adversarial Attacks [76.83548867066561]
  Instruct2Attack (I2A) is a language-guided semantic attack that generates meaningful perturbations according to free-form language instructions. We make use of state-of-the-art latent diffusion models, where we adversarially guide the reverse diffusion process to search for an adversarial latent code conditioned on the input image and text instruction. We show that I2A can successfully break state-of-the-art deep neural networks even under strong adversarial defenses.
  arXiv  Detail & Related papers  (2023-11-27T05:35:49Z)
• Graph-based Topology Reasoning for Driving Scenes [102.35885039110057]
  We present TopoNet, the first end-to-end framework capable of abstracting traffic knowledge beyond conventional perception tasks. We evaluate TopoNet on the challenging scene understanding benchmark, OpenLane-V2.
  arXiv  Detail & Related papers  (2023-04-11T15:23:29Z)
• Emergence of Maps in the Memories of Blind Navigation Agents [68.41901534985575]
  Animal navigation research posits that organisms build and maintain internal spatial representations, or maps, of their environment. We ask if machines -- specifically, artificial intelligence (AI) navigation agents -- also build implicit (or'mental') maps. Unlike animal navigation, we can judiciously design the agent's perceptual system and control the learning paradigm to nullify alternative navigation mechanisms.
  arXiv  Detail & Related papers  (2023-01-30T20:09:39Z)
• Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models [64.58271886337826]
  We study ambiguities that arise in text-to-image generative models. We propose a framework to mitigate ambiguities in the prompts given to the systems by soliciting clarifications from the user.
  arXiv  Detail & Related papers  (2022-11-17T17:12:43Z)
• Explainability Pitfalls: Beyond Dark Patterns in Explainable AI [9.020313208419378]
  We introduce explainability pitfalls (EPs), unanticipated negative downstream effects from AI explanations manifesting even when there is no intention to manipulate users. EPs are different from, yet related to, dark patterns, which are intentionally deceptive practices. We propose proactive and preventative strategies to address EPs at three interconnected levels.
  arXiv  Detail & Related papers  (2021-09-26T03:05:50Z)
• The Who in XAI: How AI Background Shapes Perceptions of AI Explanations [61.49776160925216]
  We conduct a mixed-methods study of how two different groups--people with and without AI background--perceive different types of AI explanations. We find that (1) both groups showed unwarranted faith in numbers for different reasons and (2) each group found value in different explanations beyond their intended design.
  arXiv  Detail & Related papers  (2021-07-28T17:32:04Z)
• RAIST: Learning Risk Aware Traffic Interactions via Spatio-Temporal Graph Convolutional Networks [19.582873794287632]
  A key aspect of driving a road vehicle is to interact with other road users, assess their intentions and make risk-aware tactical decisions. We propose a novel driving framework for egocentric views based on traffic graphs. We claim that our framework learns risk-aware representations by improving on the task of risk object identification.
  arXiv  Detail & Related papers  (2020-11-17T15:49:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.