Related papers: Intentionality is a Design Decision: Measuring Fun…
Developing robust and fair AI systems require datasets with comprehensive set of labels that can help ensure the validity and legitimacy of relevant measurements. Recent efforts, therefore, focus on collecting person-related datasets that…
Large-scale AI models such as GPT-4 have accelerated the deployment of artificial intelligence across critical domains including law, healthcare, and finance, raising urgent questions about trust and transparency. This study investigates…
The rapid entry of machine learning approaches in our daily activities and high-stakes domains demands transparency and scrutiny of their fairness and reliability. To help gauge machine learning models' robustness, research typically…
AI Impact Assessments are only as good as the measures used to assess the impact of these systems. It is therefore paramount that we can justify our choice of metrics in these assessments, especially for difficult to quantify ethical and…
Background: Amid the opportunities and risks introduced by generative AI, learning research needs to envision how human minds and responsibilities should re-adapt as AI augments or automates various tasks and enters daily learning,…
A key challenge in non-cooperative multi-agent systems is that of developing efficient planning algorithms for intelligent agents to interact and perform effectively among boundedly rational, self-interested agents (e.g., humans). The…
In cognitive neuroscience the sense of agency is defined as the as the experience of controlling ones own actions and, through this control, affecting the external world. At CHI 2012 I presented a paper entitled I did that! Measuring Users…
Telecommunication networks are increasingly expected to operate autonomously while supporting heterogeneous services with diverse and often conflicting intents -- that is, performance objectives, constraints, and requirements specific to…
Existing accountability frameworks for AI systems, legal, ethical, and regulatory, rest on a shared assumption: for any consequential outcome, at least one identifiable person had enough involvement and foresight to bear meaningful…
Despite actionable insight is widely recognized as the outcome of data analytics, there is a lack of a systematic and commonly-shared definition for the term. More importantly, existing definitions are generally too abstract for informing…
Active Membership Inference Test (aMINT) is a method designed to detect whether given data were used during the training of machine learning models. In Active MINT, we propose a novel multitask learning process that involves training…
Graphical User Interface (GUI) agents have the potential to assist users in interacting with complex software (e.g., PowerPoint, Photoshop). While prior research has primarily focused on automating user actions through clicks and…
State-of-the-art AI models largely lack an understanding of the cause-effect relationship that governs human understanding of the real world. Consequently, these models do not generalize to unseen data, often produce unfair results, and are…
Ensuring artificial intelligence behaves in such a way that is aligned with human values is commonly referred to as the alignment challenge. Prior work has shown that rational agents, behaving in such a way that maximizes a utility…
Determining whether another system, biological or artificial, possesses phenomenal consciousness has long been a central challenge in consciousness studies. This attribution problem has become especially pressing with the rise of large…
Recent advances in artificial intelligence have produced systems capable of remarkable performance across a wide range of tasks. These gains, however, are increasingly accompanied by concerns regarding long-horizon developmental behavior,…
Design optimizations in human-AI collaboration often focus on cognitive aspects like attention and task load. Drawing on work design literature, we propose that effective human-AI collaboration requires broader consideration of human needs…
While Chain-of-Thought (CoT) monitoring offers a unique opportunity for AI safety, this opportunity could be lost through shifts in training practices or model architecture. To help preserve monitorability, we propose a pragmatic way to…
Ranking ensemble is a critical component in real recommender systems. When a user visits a platform, the system will prepare several item lists, each of which is generally from a single behavior objective recommendation model. As multiple…
Long-term action anticipation from egocentric video is critical for applications such as human-computer interaction and assistive technologies, where anticipating user intent enables proactive and context-aware AI assistance. However,…