Tracking the perspectives of interacting language models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |