How Much More Probable is "Much More Probable"? Verbal Expressions for Probability Updates
This work addresses the need for explainable AI by improving how systems communicate probability changes to users, though it is incremental as it builds on prior research on absolute probabilities.
The study tackled the problem of translating numerical probability updates into natural language phrases like 'much more likely' for Bayesian inference systems, finding that a fixed difference in probability best matched human usage with 72% accuracy.
Bayesian inference systems should be able to explain their reasoning to users, translating from numerical to natural language. Previous empirical work has investigated the correspondence between absolute probabilities and linguistic phrases. This study extends that work to the correspondence between changes in probabilities (updates) and relative probability phrases, such as "much more likely" or "a little less likely." Subjects selected such phrases to best describe numerical probability updates. We examined three hypotheses about the correspondence, and found the most descriptively accurate of these three to be that each such phrase corresponds to a fixed difference in probability (rather than fixed ratio of probabilities or of odds). The empirically derived phrase selection function uses eight phrases and achieved a 72% accuracy in correspondence with the subjects' actual usage.