Extending rational models of communication from beliefs to actions
This work addresses a foundational problem in computational linguistics by integrating belief and action models, offering incremental insights into rational communication through richer decision problems.
The authors tackled the challenge of distinguishing belief- and action-based objectives in computational models of communication by introducing a new paradigm called signaling bandits, which generalizes classic signaling games to a multi-armed bandit setting. They developed three speaker models and found that grounding production choices in future listener actions leads to relevance effects and flexible nonliteral language use.
Speakers communicate to influence their partner's beliefs and shape their actions. Belief- and action-based objectives have been explored independently in recent computational models, but it has been challenging to explicitly compare or integrate them. Indeed, we find that they are conflated in standard referential communication tasks. To distinguish these accounts, we introduce a new paradigm called signaling bandits, generalizing classic Lewis signaling games to a multi-armed bandit setting where all targets in the context have some relative value. We develop three speaker models: a belief-oriented speaker with a purely informative objective; an action-oriented speaker with an instrumental objective; and a combined speaker which integrates the two by inducing listener beliefs that generally lead to desirable actions. We then present a series of simulations demonstrating that grounding production choices in future listener actions results in relevance effects and flexible uses of nonliteral language. More broadly, our findings suggest that language games based on richer decision problems are a promising avenue for insight into rational communication.