Search for: All records

Personalising decision-making assistance to different users and tasks can improve human-AI team performance, such as by appropriately impacting reliance on AI assistance. However, people are different in many ways, with many hidden qualities, and adapting AI assistance to these hidden qualities is difficult. In this work, we consider a hidden quality previously identified as important: overreliance on AI assistance. We would like to (i) quickly determine the value of this hidden quality, and (ii) personalise AI assistance based on this value. In our first study, we introduce a few probe questions (where we know the true answer) to determine if a user is an overrelier or not, finding that correctly-chosen probe questions work well. In our second study, we improve human-AI team performance, personalising AI assistance based on users’ overreliance quality. Exploratory analysis indicates that people learn different strategies of using AI assistance depending on what AI assistance they saw previously, indicating that we may need to take this into account when designing adaptive AI assistance. We hope that future work will continue exploring how to infer and personalise to other important hidden qualities. 

Researchers discuss approaches, such as defining concrete milestones, that could enhance AI’s positive impact in the near future. The article also presents a nonprofit organization with a novel approach to fund work toward these goals, including data on its first call for proposals. 

Abstract Psychological stress is a key driver of short-term blood pressure (BP) elevations and cardiovascular risk, yet its moment-to-moment impact in daily life remains difficult to predict. In this longitudinal observational study, we collected multimodal data from 20 adults with self-reported hypertension, including continuous wearable-derived heart rate and activity, ecological momentary assessment (EMA) stress ratings, and ambulatory BP measurements in free-living conditions. The dataset comprised 3694 EMA responses and 3812 BP measurements collected over approximately four weeks per participant (mean 24.1 ± 8.5 days). We evaluated whether participant-specific (“personalized”) models outperform a single pooled population model. Two prediction tasks were examined: (i) prediction of near-term BP elevations from wearable signals and stress EMA responses and (ii) prediction of self-reported stress from wearable signals and BP. Across both tasks, personalized models consistently improved predictive performance. For BP prediction, personalized models achieved a mean AUROC of 0.803, exceeding the population model by 0.235, while for stress prediction they achieved a mean AUROC of 0.849, exceeding the population model by 0.208. These findings suggest that personalized wearable-based models can capture individual patterns of stress and BP dynamics, with direct implications for precision mental health assessment and just-in-time adaptive intervention design in future work. 

In settings where an AI agent nudges a human agent toward a goal, the AI can quickly learn a high-quality policy by modeling the human well. Despite behavioral evidence that humans hyperbolically discount future rewards, we model human as Markov Decision Processes (MDPs) with exponential discounting. This is because planning is difficult with non-exponential discounts. In this work, we investigate whether the performance benefits of modeling humans as hyperbolic discounters outweigh the computational costs. We focus on AI interventions that change the human's discounting (i.e. decreases the human's "nearsightedness" to help them toward distant goals). We derive a fixed exponential discount factor that can approximate hyperbolic discounting, and prove that this approximation guarantees the AI will never miss a necessary intervention. We also prove that our approximation causes fewer false positives (unnecessary interventions) than the mean hazard rate, another well-known method for approximating hyperbolic MDPs as exponential ones. Surprisingly, our experiments demonstrate that exponential approximations outperform hyperbolic ones in online learning, even when the ground-truth human MDP is hyperbolically discounted. 

We provide new connections between two distinct federated learning approaches based on (i) ADMM and (ii) Variational Bayes (VB), and propose new variants by combining their complementary strengths. Specifically, we show that the dual variables in ADMM naturally emerge through the "site" parameters used in VB with isotropic Gaussian covariances. Using this, we derive two versions of ADMM from VB that use flexible covariances and functional regularisation, respectively. Through numerical experiments, we validate the improvements obtained in performance. The work shows connection between two fields that are believed to be fundamentally different and combines them to improve federated learning.