Related papers: From Overload to Convergence: Supporting Multi-Iss…
Humans and AIs are often paired on decision tasks with the expectation of achieving complementary performance -- where the combination of human and AI outperforms either one alone. However, how to improve performance of a human-AI team is…
In human-AI decision making, designing AI that complements human expertise has been a natural strategy to enhance human-AI collaboration, yet it often comes at the cost of decreased AI performance in areas of human strengths. This can…
Given that Artificial Intelligence (AI) increasingly permeates our lives, it is critical that we systematically align AI objectives with the goals and values of humans. The human-AI alignment problem stems from the impracticality of…
The desirable properties of explanations in information systems have fueled the demands for transparency in artificial intelligence (AI) outputs. To address these demands, the field of explainable AI (XAI) has put forth methods that can…
In recent years, artificial intelligence (AI) decision-making and autonomous systems became an integrated part of the economy, industry, and society. The evolving economy of the human-AI ecosystem raising concerns regarding the risks and…
AI systems increasingly assist human decision making by producing preliminary assessments of complex inputs. However, such AI-generated assessments can often be noisy or systematically biased, raising a central question: how should costly…
As AI becomes more deeply embedded in knowledge work, building assistants that support human creativity and expertise becomes more important. Yet achieving synergy in human-AI collaboration is not easy. Providing AI with detailed…
We formalize AI alignment as a multi-objective optimization problem called $\langle M,N,\varepsilon,\delta\rangle$-agreement, in which a set of $N$ agents (including humans) must reach approximate ($\varepsilon$) agreement across $M$…
Many domains now employ AI-based decision-making aids, and although the potential for AI systems to assist with decision making is much discussed, human-AI collaboration often underperforms due to factors such as (mis)trust in the AI system…
With the increased adoption of artificial intelligence (AI) in industry and society, effective human-AI interaction systems are becoming increasingly important. A central challenge in the interaction of humans with AI is the estimation of…
Human-AI teams play a pivotal role in improving overall system performance when neither the human nor the model can achieve such performance on their own. With the advent of powerful and accessible Generative AI models, several mundane…
AI companions enable deep emotional relationships by engaging a user's sense of identity, but they also pose risks like unhealthy emotional dependence. Mitigating these risks requires first understanding the underlying process of identity…
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…
We anticipate increased instances of humans and AI systems working together in what we refer to as a hybrid team. The increase in collaboration is expected as AI systems gain proficiency and their adoption becomes more widespread. However,…
Automated systems that negotiate with humans have broad applications in pedagogy and conversational AI. To advance the development of practical negotiation systems, we present CaSiNo: a novel corpus of over a thousand negotiation dialogues…
We describe a class of tasks called decision-oriented dialogues, in which AI assistants such as large language models (LMs) must collaborate with one or more humans via natural language to help them make complex decisions. We formalize…
The use of Artificial Intelligence (AI) in high-risk, decision-making scenarios presents technical, safety, and normative challenges; problems that may only be ameliorated by human oversight. However, notions of human oversight lack a…
Human computer interaction is shifting from screen-based systems to multimodal interfaces where artificial intelligence powered systems increasingly interpret user intent through speech, gesture, and gaze. Yet users rarely understand how…
Despite impressive performance in many benchmark datasets, AI models can still make mistakes, especially among out-of-distribution examples. It remains an open question how such imperfect models can be used effectively in collaboration with…
Developing safe and useful general-purpose AI systems will require us to make progress on scalable oversight: the problem of supervising systems that potentially outperform us on most skills relevant to the task at hand. Empirical work on…