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

2025-02-25

AI Summary

Existing AI-mediated communication research predominantly adheres to a unidirectional information transmission paradigm, overlooking the large language model’s (LLM) active, collaborative role in co-constructing meaning. Method: We propose a subjectivity-objectivity co-adaptive AI-mediated communication model featuring a dual-LLM agent architecture that dynamically reconstructs human–human textual dialogue via real-time intent recognition, semantic rewriting, empathy modeling, and dialogic regulation. Contribution/Results: Moving beyond traditional transmission-oriented frameworks, our model targets shared meaning generation, enabling personalized, context-aware, and real-time message adaptation. Evaluation on a prototype system demonstrates significant improvements over baselines: +27% dialogue coherence, −34% misinterpretation rate, and markedly increased collaboration willingness (p < 0.01). This work pioneers the conceptualization of LLMs as bidirectional meaning co-constructors in communication—establishing a novel paradigm for explainable, customizable, and empathy-driven human–AI collaboration.

Technology Category

• Multiagent Systems: Agent Communication
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Human-AI Collaboration / Human-AI Teaming

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

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.

Problem

• Enhances human-human text chat
• Utilizes LLM-based adaptive agents
• Facilitates real-time message shaping

Innovation

• LLM-based adaptive agents
• Real-time message shaping
• Customizable communication design