Tracking the perspectives of interacting language models

Hayden Helm, Brandon Duderstadt, Youngser Park, Carey Priebe


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.
Anthology ID:
2024.emnlp-main.90
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1508–1519
Language:
URL:
https://aclanthology.org/2024.emnlp-main.90
DOI:
Bibkey:
Cite (ACL):
Hayden Helm, Brandon Duderstadt, Youngser Park, and Carey Priebe. 2024. Tracking the perspectives of interacting language models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 1508–1519, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Tracking the perspectives of interacting language models (Helm et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.90.pdf