AI-Generated Compromises for Coalition Formation: Modeling, Simulation, and a Textual Case Study
This work addresses the challenge of facilitating large-scale democratic text editing, such as constitution drafting, which is incremental by building on existing coalition formation processes.
The paper tackles the problem of finding compromise proposals for coalition formation in AI, particularly in collaborative text editing like drafting a constitution, by developing AI models using NLP and LLMs to generate such compromises, and demonstrates their effectiveness through simulations.
The challenge of finding compromises between agent proposals is fundamental to AI sub-fields such as argumentation, mediation, and negotiation. Building on this tradition, Elkind et al. (2021) introduced a process for coalition formation that seeks majority-supported proposals preferable to the status quo, using a metric space where each agent has an ideal point. The crucial step in this iterative process involves identifying compromise proposals around which agent coalitions can unite. How to effectively find such compromise proposals, however, remains an open question. We address this gap by formalizing a holistic model that encompasses agent bounded rationality and uncertainty and developing AI models to generate such compromise proposals. We focus on the domain of collaboratively writing text documents -- e.g., to enable the democratic creation of a community constitution. We apply NLP (Natural Language Processing) techniques and utilize LLMs (Large Language Models) to create a semantic metric space for text and develop algorithms to suggest suitable compromise points. To evaluate the effectiveness of our algorithms, we simulate various coalition formation processes and demonstrate the potential of AI to facilitate large-scale democratic text editing, such as collaboratively drafting a constitution, an area where traditional tools are limited.