Related papers: Explaining and Improving Information Complementari…
This paper introduces X-SHAP, a model-agnostic method that assesses multiplicative contributions of variables for both local and global predictions. This method theoretically and operationally extends the so-called additive SHAP approach.…
The visual analytics community has long aimed to understand users better and assist them in their analytic endeavors. As a result, numerous conceptual models of visual analytics aim to formalize common workflows, techniques, and goals…
Despite recent advances in the field of explainable artificial intelligence systems, a concrete quantitative measure for evaluating the usability of such systems is nonexistent. Ensuring the success of an explanatory interface in…
As AI systems become increasingly integrated into high-stakes domains, enabling users to accurately interpret model behavior is critical. While AI explanations can be provided, users often struggle to reason effectively with these…
We evaluate two popular local explainability techniques, LIME and SHAP, on a movie recommendation task. We discover that the two methods behave very differently depending on the sparsity of the data set. LIME does better than SHAP in dense…
Integrating AI in healthcare can greatly improve patient care and system efficiency. However, the lack of explainability in AI systems (XAI) hinders their clinical adoption, especially in multimodal settings that use increasingly complex…
We study the implementability of stable matchings in a two-sided market model with one-sided incomplete information. Firms' types are publicly known, whereas workers' types are private information. A mechanism generates a matching and…
In this preprint, we present A collaborative human-AI approach to building an inspectable semantic layer for Agentic AI. AI agents first propose candidate knowledge structures from diverse data sources; domain experts then validate,…
The integration of Artificial Intelligence (AI) into high-stakes domains such as healthcare, finance, and autonomous systems is often constrained by concerns over transparency, interpretability, and trust. While Human-Centered AI (HCAI)…
The Information Bottleneck (IB) framework is a general characterization of optimal representations obtained using a principled approach for balancing accuracy and complexity. Here we present a new framework, the Dual Information Bottleneck…
AI systems increasingly support human decision-making. In many cases, despite the algorithm's superior performance, the final decision remains in human hands. For example, an AI may assist doctors in determining which diagnostic tests to…
Inventory control is a fundamental operations problem in which ordering decisions are traditionally guided by theoretically grounded operations research (OR) algorithms. However, such algorithms often rely on rigid modeling assumptions and…
We formalize AI-human collaboration through an agent-based simulation that distinguishes optimization-based AI search from satisficing-based human adaptation. Using an NK model, we examine how these distinct decision heuristics interact…
Current evaluations of agents remain centered around one-shot task completion, failing to account for the inherently iterative and collaborative nature of many real-world problems, where human goals are often underspecified and evolve. We…
We study allocation problems without monetary transfers where agents have correlated types, i.e., hold private information about one another. Such peer information is relevant in various settings, including science funding, allocation of…
Modern news is often comprehensive, weaving together information from diverse domains, including technology, finance, and agriculture. This very comprehensiveness creates a challenge for interpretation, as audiences typically possess…
Reproducing scientific analyses is essential for preserving knowledge, building extensible codebases, and deepening researcher understanding - yet the effort often outweighs its academic recognition. We argue that the reproduction of…
The human-agent team, which is a problem in which humans and autonomous agents collaborate to achieve one task, is typical in human-AI collaboration. For effective collaboration, humans want to have an effective plan, but in realistic…
Integrated information theory (IIT) is a theoretical framework that provides a quantitative measure to estimate when a physical system is conscious, its degree of consciousness, and the complexity of the qualia space that the system is…
In order to engender trust in AI, humans must understand what an AI system is trying to achieve, and why. To overcome this problem, the underlying AI process must produce justifications and explanations that are both transparent and…