The Open-domain Paradox for Chatbots: Common Ground as the Basis for Human-like Dialogue
This addresses a fundamental issue in chatbot design for users seeking more natural and engaging interactions, but it is incremental as it builds on existing theories without presenting new empirical results.
The paper tackles the problem that open-domain chatbots, despite being designed for broad conversation, often produce narrow dialogue when given minimal constraints, a phenomenon termed the 'open-domain paradox'. It explains this using the theory of common ground and proposes paths to improve human-computer dialogue.
There is a surge in interest in the development of open-domain chatbots, driven by the recent advancements of large language models. The "openness" of the dialogue is expected to be maximized by providing minimal information to the users about the common ground they can expect, including the presumed joint activity. However, evidence suggests that the effect is the opposite. Asking users to "just chat about anything" results in a very narrow form of dialogue, which we refer to as the "open-domain paradox". In this position paper, we explain this paradox through the theory of common ground as the basis for human-like communication. Furthermore, we question the assumptions behind open-domain chatbots and identify paths forward for enabling common ground in human-computer dialogue.