# Tracking the perspectives of interacting language models

arXiv: https://arxiv.org/abs/2406.11938 · HTML: https://mlsanity.com/paper/2406.11938/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Builds on (most cited first, 28 of 28)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [The Curse of Recursion: Training on Generated Data Makes Models Forget](https://mlsanity.com/paper/2305.17493/) (2023)
- [Nomic Embed: Training a Reproducible Long Context Text Embedder](https://mlsanity.com/paper/2402.01613/) (2024)
- [Evaluating Large Language Models in Theory of Mind Tasks](https://mlsanity.com/paper/2302.02083/) (2023)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [Machine Culture](https://mlsanity.com/paper/2311.11388/) (2023)
- [Network Formation and Dynamics Among Multi-LLMs](https://mlsanity.com/paper/2402.10659/) (2024)
- [GraSPy: Graph Statistics in Python](https://mlsanity.com/paper/1904.05329/) (2019)
- [Comparing Foundation Models using Data Kernels](https://mlsanity.com/paper/2305.05126/) (2023)
- [Towards a theory of out-of-distribution learning](https://mlsanity.com/paper/2109.14501/) (2021)
- [Out-of-sample extension of graph adjacency spectral embedding](https://mlsanity.com/paper/1802.06307/) (2018)
- [A Statistical Turing Test for Generative Models](https://mlsanity.com/paper/2309.08913/) (2023)
- [Mental State Classification Using Multi-graph Features](https://mlsanity.com/paper/2203.00516/) (2022)
- [A partition-based similarity for classification distributions](https://mlsanity.com/paper/2011.06557/) (2020)
- [Dynamic Silos: Increased Modularity in Intra-organizational Communication Networks during the Covid-19 Pandemic](https://mlsanity.com/paper/2104.00641/) (2021)

## Built on by (most cited first, 14 of 14)

- [When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings](https://mlsanity.com/paper/2407.04503/) (2024)
- [LLM as a Broken Telephone: Iterative Generation Distorts Information](https://mlsanity.com/paper/2502.20258/) (2025)
- [Consistent estimation of generative model representations in the data kernel perspective space](https://mlsanity.com/paper/2409.17308/) (2024)
- [Statistical inference on black-box generative models in the data kernel perspective space](https://mlsanity.com/paper/2410.01106/) (2024)
- [LLM Web Dynamics: Tracing Model Collapse in a Network of LLMs](https://mlsanity.com/paper/2506.15690/) (2025)
- [Investigating social alignment via mirroring in a system of interacting language models](https://mlsanity.com/paper/2412.06834/) (2024)
- [Detecting Perspective Shifts in Multi-agent Systems](https://mlsanity.com/paper/2512.05013/) (2025)
- [Gaussian mixture models as a proxy for interacting language models](https://mlsanity.com/paper/2506.00077/) (2025)
- [Query-efficient model evaluation using cached responses](https://mlsanity.com/paper/2605.07096/) (2026)
- [Toward a digital twin of U.S. Congress](https://mlsanity.com/paper/2505.00006/) (2025)
- [Concentration bounds on response-based vector embeddings of black-box generative models](https://mlsanity.com/paper/2511.08307/) (2025)
- [Black-box model classification under the discriminative factorization](https://mlsanity.com/paper/2605.07878/) (2026)
- [Control Charts for Multi-agent Systems](https://mlsanity.com/paper/2605.11135/) (2026)
- [Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models](https://mlsanity.com/paper/2605.26409/) (2026)

## Abstract (arXiv)

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.