Papers for

pilot training instructors

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

People understand shorter ai alerts faster in urgent tasks

Must AI Spell It Out? Pragmatic Comprehension of Alerts in a Time-Critical Task

Abstract: Assistive systems typically tell users everything, often spending time and attention on what a user already knows, leaving less for what happens next. People, on the other hand, leave out what they expect the listener can supply. Can people use their prior knowledge to understand an incomplete message when the speaker is a machine though? We studied this pragmatic comprehension in a monitoring task controlling users' prior knowledge and the available time to detect critical situations. In a preregistered study (N=114), we compared a pragmatic planner that reasons over a model of the listener's knowledge to decide what to say, when, and how explicitly, with a baseline specifying problems fully in onset order. Participants resolved underspecified alerts almost as reliably as fully specified ones and sooner, detected more problems, and rated the pragmatic assistant helpful more often, with no increase in reported mental demand. Our findings show that people can recover what the system left implicit and that pragmatic communication can support effective assistance under the constraints of a changing world.

Mon 2 NovHuman-Computer InteractionArtificial IntelligenceComputation and Language
The gist
Sometimes, AI assistants give very detailed warnings that repeat what users already know, which wastes time and attention. This paper shows that people can understand shorter, less detailed alerts if they already have some background knowledge. The authors ran a study where people controlled a monitoring task and found that these shorter alerts helped people spot problems faster and more often, without causing extra mental stress. This means AI can be more efficient by leaving out details users can fill in themselves.
Open → 2611.03976v1