Related papers: The Scenic Route to Deception: Dark Patterns and E…
While generative AI enables high-fidelity UI generation from text prompts, users struggle to articulate design intent and evaluate or refine results-creating gulfs of execution and evaluation. To understand the information needed for UI…
Despite the practical success of Artificial Intelligence (AI), current neural AI algorithms face two significant issues. First, the decisions made by neural architectures are often prone to bias and brittleness. Second, when a chain of…
Large, pretrained language models infer powerful representations that encode rich semantic and syntactic content, albeit implicitly. In this work we introduce a novel neural language model that enforces, via inductive biases, explicit…
Explainability is an essential reason limiting the application of neural networks in many vital fields. Although neuro-symbolic AI hopes to enhance the overall explainability by leveraging the transparency of symbolic learning, the results…
Traditional path-planning techniques treat humans as obstacles. This has changed since robots started to enter human environments. On modern robots, social navigation has become an important aspect of navigation systems. To use…
Generative AI systems increasingly expose powerful reasoning and image refinement capabilities through user-facing chatbot interfaces. In this work, we show that the na\"ive exposure of such capabilities fundamentally undermines modern…
Similarly to other connectionist models, Graph Neural Networks (GNNs) lack transparency in their decision-making. A number of sub-symbolic approaches have been developed to provide insights into the GNN decision making process. These are…
This research examines the emerging technique of step-around prompt engineering in GenAI research, a method that deliberately bypasses AI safety measures to expose underlying biases and vulnerabilities in GenAI models. We discuss how…
Generative AI (GenAI) tools are transforming information seeking, but their fluent, authoritative responses risk overreliance and discourage independent verification and reasoning. Rather than replacing the cognitive work of users, GenAI…
Graph neural networks (GNNs) are quickly becoming the standard approach for learning on graph structured data across several domains, but they lack transparency in their decision-making. Several perturbation-based approaches have been…
Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and…
The ability to navigate robots with natural language instructions in an unknown environment is a crucial step for achieving embodied artificial intelligence (AI). With the improving performance of deep neural models proposed in the field of…
Deceptive UI designs, widely instantiated across the web and commonly known as dark patterns, manipulate users into performing actions misaligned with their goals. In this paper, we show that dark patterns are highly effective in steering…
The experience and adoption of conversational search is tied to the accuracy and completeness of users' mental models -- their internal frameworks for understanding and predicting system behaviour. Thus, understanding these models can…
This essay examines how Generative AI (GenAI) is rapidly transforming design practices and how discourse often falls into over-simplified narratives that impede meaningful research and practical progress. We identify and deconstruct five…
As semi-autonomous vehicles (AVs) become prevalent, drivers must collaborate with AI systems whose decision-making processes remain opaque. This study examines how drivers of AVs develop folk theories to interpret algorithmic behavior that…
Recent applications of autonomous agents and robots, such as self-driving cars, scenario-based trainers, exploration robots, and service robots have brought attention to crucial trust-related challenges associated with the current…
Neurosymbolic AI combines the interpretability, parsimony, and explicit reasoning of classical symbolic approaches with the statistical learning of data-driven neural approaches. Models and policies that are simultaneously differentiable…
Designing plausible network models typically requires scholars to form a priori intuitions on the key drivers of network formation. Oftentimes, these intuitions are supported by the statistical estimation of a selection of network evolution…
The opaqueness of many complex machine learning algorithms is often mentioned as one of the main obstacles to the ethical development of artificial intelligence (AI). But what does it mean for an algorithm to be opaque? Highly complex…