A Dynamic Approach to Collaborative Document Writing (Full Version)

TL;DR

This paper presents a dynamic model for collaborative document writing where agents propose and vote on paragraphs, aiming for stable, high-welfare outcomes, supported by simulations using NLP and LLMs.

Contribution

It introduces a novel dynamic voting-based framework for collaborative text creation and explores its properties through formalization and agent-based simulations.

Findings

Demonstrates the potential for rapid convergence to high social welfare in collaborative writing.

Provides formal analysis of stability and welfare in dynamic aggregation processes.

Shows promising results using NLP and LLMs in simulated collaborative environments.

Abstract

We introduce a model for collaborative text aggregation in which an agent community coauthors a document, modeled as an unordered collection of paragraphs, using a dynamic mechanism: agents propose paragraphs and vote on those suggested by others. We formalize the setting and explore its realizations, concentrating on voting mechanisms that aggregate votes into a single, dynamic document. We focus on two desiderata: the eventual stability of the process and its expected social welfare. Following an impossibility result, we describe several aggregation methods and report on agent-based simulations that utilize natural language processing (NLP) and large-language models (LLMs) to model agents and their contexts. Using these simulations, we demonstrate promising results regarding the possibility of rapid convergence to a high social welfare collaborative text.