AI-Generated Compromises for Coalition Formation

TL;DR

This paper develops AI methods using NLP and large language models to generate compromise proposals in coalition formation, facilitating democratic text editing.

Contribution

It formalizes a model incorporating agent bounded rationality and uncertainty, and designs algorithms to suggest broadly supported compromise proposals in collaborative writing.

Findings

AI can generate compromise proposals likely to receive broad support

Simulations show AI facilitates large-scale democratic text editing

NLP techniques induce a semantic metric space over text

Abstract

The challenge of finding compromises between agent proposals is fundamental to AI subfields 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. A crucial step in this process involves identifying compromise proposals around which agent coalitions can unite. How to effectively find such compromise proposals remains an open question. We address this gap by formalizing a model that incorporates agent bounded rationality and uncertainty, and by developing AI methods to generate compromise proposals. We focus on the domain of collaborative document writing, such as the democratic drafting of a community constitution. Our approach uses natural language processing techniques and large language models to induce a semantic metric space over text. Based on this space, we design algorithms to suggest compromise points likely to receive broad support. To evaluate our methods, we simulate coalition formation processes and show that AI can facilitate large-scale democratic text editing, a domain where traditional tools are limited.