The Open-domain Paradox for Chatbots: Common Ground as the Basis for Human-like Dialogue

TL;DR

This paper discusses the 'open-domain paradox' in chatbots, where minimal guidance leads to narrow conversations, and explores how establishing common ground can improve human-like dialogue.

Contribution

It introduces the open-domain paradox, analyzes its causes through common ground theory, and suggests new directions for developing more effective open-domain chatbots.

Findings

Minimal guidance often results in narrow dialogues

Common ground is essential for human-like communication

Future work should focus on establishing common ground in chatbots

Abstract

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.