Speculating About Multi-user Conversational Interfaces and LLMs: What If Chatting Wasn't So Lonely?

TL;DR

This paper explores the potential for multi-user conversational interfaces powered by large language models to improve group interactions, addressing technical, legal, and design challenges and drawing inspiration from group discussion paradigms.

Contribution

It proposes new approaches for multi-user CUIs using LLMs, inspired by group discussion methods, to overcome existing implementation challenges.

Findings

Identifies key challenges in multi-user CUI design and implementation.

Suggests leveraging parliamentary and consensus paradigms for better group interactions.

Highlights potential to reduce poorly run meetings with improved multi-user interfaces.

Abstract

The advent of LLMs means that CUIs are cool again, but what isn't so cool is that we're doomed to use them alone. The one user, one account, one device paradigm has dominated the design of CUIs and is not going away as new conversational technologies emerge. In this provocation we explore some of the technical, legal, and design difficulties that seem to make multi-user CUIs so difficult to implement. Drawing inspiration from the ways that people manage messy group discussions, such as parliamentary and consensus-based paradigms, we show how LLM-based CUIs might be well suited to bridging the gap. With any luck, this might even result in everyone having to sit through fewer poorly run meetings and agonising group discussions - truly a laudable goal!