Skip to main content

Faculty & Research


Ambiguity Can Compensate for Semantic Differences in Human-AI Communication

Journal Article
Ambiguity and semantic differences are each known to be independent sources of communication difficulty. However, the authors show using computational models that ambiguity can compensate for semantic differences across communicators. Given the heterogeneity of humans with which artificial systems interact, semantic differences will be the norm. Therefore each time a machine starts to communicate with a new user, the authors' results suggest it will do well to start with a moderately ambiguous code in order to more effectively bridge semantic differences. The authors dub this the “adaptive ambiguity” hypothesis.

Professor of Strategy