Tracking the perspectives of interacting language models

TL;DR

This paper introduces a formal framework for modeling and analyzing the perspectives of interacting large language models within a communication network, exploring how information diffuses among them in simulated environments.

Contribution

It formalizes the concept of LLM communication networks and provides a method to represent individual model perspectives, enabling systematic study of information diffusion.

Findings

Information diffusion varies with network structure

Models develop distinct perspectives over interactions

Communication networks influence knowledge propagation

Abstract

Large language models (LLMs) are capable of producing high quality information at unprecedented rates. As these models continue to entrench themselves in society, the content they produce will become increasingly pervasive in databases that are, in turn, incorporated into the pre-training data, fine-tuning data, retrieval data, etc. of other language models. In this paper we formalize the idea of a communication network of LLMs and introduce a method for representing the perspective of individual models within a collection of LLMs. Given these tools we systematically study information diffusion in the communication network of LLMs in various simulated settings.