Related papers: Towards Scalable Oversight via Partitioned Human S…
Artificial Intelligence (AI) systems are not intrinsically neutral and biases trickle in any type of technological tool. In particular when dealing with people, the impact of AI algorithms' technical errors originating with mislabeled data…
Existing AI evaluation practices often fail to capture how systems actually perform in low-resource environments, where operational constraints shape usability as much as model quality. Through a structured analysis of existing benchmark…
Artificial intelligence systems, particularly large language models (LLMs), are increasingly being employed in high-stakes decisions that impact both individuals and society at large, often without adequate safeguards to ensure safety,…
As artificial intelligence becomes increasingly pervasive and powerful, the ability to audit AI-based systems is growing in importance. However, explainability for artificial intelligence systems is not a one-size-fits-all solution;…
Common methods for aligning already-capable models with desired behavior rely on the ability of humans to provide supervision. However, future superhuman models will surpass the capability of humans. Therefore, humans will only be able to…
The rapid advancement of AI has expanded its capabilities across domains, yet introduced critical technical vulnerabilities, such as algorithmic bias and adversarial sensitivity, that pose significant societal risks, including…
Manufacturing lines, service journeys, supply chains, and AI reasoning chains share a common challenge: attributing a terminal outcome to the intermediate stage that caused it. We establish an information-theoretic barrier to this credit…
A significant proportion of clinical physiologic monitoring alarms are false. This often leads to alarm fatigue in clinical personnel, inevitably compromising patient safety. To combat this issue, researchers have attempted to build Machine…
We outline a vision for frontier AI auditing, which we define as rigorous third-party verification of frontier AI developers' safety and security claims, and evaluation of their systems and practices against relevant standards, based on…
Semi-supervised learning holds great promise for many real-world applications, due to its ability to leverage both unlabeled and expensive labeled data. However, most semi-supervised learning algorithms still heavily rely on the limited…
In typical medical image classification problems, labeled data is scarce while unlabeled data is more available. Semi-supervised learning and self-supervised learning are two different research directions that can improve accuracy by…
The increasing adoption of AI systems in hiring has raised concerns about algorithmic bias and accountability, prompting regulatory responses including the EU AI Act, NYC Local Law 144, and Colorado's AI Act. While existing research…
In the rapidly evolving field of artificial intelligence (AI), traditional benchmarks can fall short in attempting to capture the nuanced capabilities of AI models. We focus on the case of physical world modeling and propose a novel…
Security Operations Centers (SOCs) face growing challenges in managing cybersecurity threats due to an overwhelming volume of alerts, a shortage of skilled analysts, and poorly integrated tools. Human-AI collaboration offers a promising…
Recent works in artificial intelligence fairness attempt to mitigate discrimination by proposing constrained optimization programs that achieve parity for some fairness statistic. Most assume availability of the class label, which is…
The integration of human and artificial intelligence offers a powerful avenue for advancing our understanding of information processing, as each system provides unique computational insights. However, despite the promise of human-AI…
As humans increasingly rely on multiround conversational AI for high stakes decisions, principled frameworks are needed to ensure such interactions reliably improve decision quality. We adopt a human centric view governed by two principles:…
In recent years, Explainable AI (xAI) attracted a lot of attention as various countries turned explanations into a legal right. xAI allows for improving models beyond the accuracy metric by, e.g., debugging the learned pattern and…
Artificial Intelligence (AI) increasingly shows its potential to outperform predicate logic algorithms and human control alike. In automatically deriving a system model, AI algorithms learn relations in data that are not detectable for…
Physiological measurements involves observing variables that attribute to the normative functioning of human systems and subsystems directly or indirectly. The measurements can be used to detect affective states of a person with aims such…