Question Asking as Program Generation
This work addresses the challenge of understanding and replicating human question-asking for AI systems, but it is incremental as it builds on existing cognitive modeling approaches.
The authors tackled the problem of modeling human-like question generation by treating questions as executable programs, and found that their model predicts human questions and generates novel ones not seen in training.
A hallmark of human intelligence is the ability to ask rich, creative, and revealing questions. Here we introduce a cognitive model capable of constructing human-like questions. Our approach treats questions as formal programs that, when executed on the state of the world, output an answer. The model specifies a probability distribution over a complex, compositional space of programs, favoring concise programs that help the agent learn in the current context. We evaluate our approach by modeling the types of open-ended questions generated by humans who were attempting to learn about an ambiguous situation in a game. We find that our model predicts what questions people will ask, and can creatively produce novel questions that were not present in the training set. In addition, we compare a number of model variants, finding that both question informativeness and complexity are important for producing human-like questions.