Model-agnostic Fits for Understanding Information Seeking Patterns in Humans
This work provides a model-agnostic approach to understanding human information-seeking behavior, which is significant for computational modeling of human cognition and human-AI interfaces.
This paper re-examines existing experimental data on human information-seeking biases, using deep learning models to replicate aggregate biases and capture individual variations. They found that large population samples can compensate for limited individual data, enabling high-accuracy prediction of human behavior without assumptions about task goals or reward structures.
In decision making tasks under uncertainty, humans display characteristic biases in seeking, integrating, and acting upon information relevant to the task. Here, we reexamine data from previous carefully designed experiments, collected at scale, that measured and catalogued these biases in aggregate form. We design deep learning models that replicate these biases in aggregate, while also capturing individual variation in behavior. A key finding of our work is that paucity of data collected from each individual subject can be overcome by sampling large numbers of subjects from the population, while still capturing individual differences. In addition, we can predict human behavior with high accuracy without making any assumptions about task goals, reward structure, or individual biases, thus providing a model-agnostic fit to human behavior in the task. Such an approach can sidestep potential limitations in modeler-specified inductive biases, and has implications for computational modeling of human cognitive function in general, and of human-AI interfaces in particular.