Intersubjective Model of AI-mediated Communication: Augmenting Human-Human Text Chat through LLM-based Adaptive Agent Pair

TL;DR

This paper introduces the Intersubjective Model, a novel framework for AI-mediated communication that uses adaptive LLM-based agents to dynamically shape messages and enhance shared understanding in human-human chat.

Contribution

The paper proposes a new intersubjective communication model leveraging LLMs to actively augment and customize human-human interactions, moving beyond traditional message transmission.

Findings

Developed a prototype chat system based on the Intersubjective Model.

Demonstrated potential for adaptive message shaping in real-time communication.

Explored the design space for AI-augmented human interaction.

Abstract

The growing prevalence of Large Language Models (LLMs) is reshaping online text-based communication; a transformation that is extensively studied as AI-mediated communication. However, much of the existing research remains bound by traditional communication models, where messages are created and transmitted directly between humans despite LLMs being able to play a more active role in transforming messages. In this work, we propose the Intersubjective Model of AI-mediated Communication, an alternative communication model that leverages LLM-based adaptive agents to augment human-human communication. Unlike traditional communication models that focus on the accurate transmission of information, the Intersubjective Model allows for communication to be designed in an adaptive and customizable way to create alternative interactions by dynamically shaping messages in real time and facilitating shared understanding between the human participants. In this paper, we have developed a prototype text chat system based on the Intersubjective Model to describe the potential of this model, as well as the design space it affords.