Tracking the perspectives of interacting language models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Helm, Hayden, Duderstadt, Brandon, Park, Youngser, Priebe, Carey E.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909225903456256
author Helm, Hayden
Duderstadt, Brandon
Park, Youngser
Priebe, Carey E.
author_facet Helm, Hayden
Duderstadt, Brandon
Park, Youngser
Priebe, Carey E.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_11938
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Tracking the perspectives of interacting language models
Helm, Hayden
Duderstadt, Brandon
Park, Youngser
Priebe, Carey E.
Artificial Intelligence
Multiagent Systems
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.
title Tracking the perspectives of interacting language models
topic Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2406.11938