# LLM as a Broken Telephone: Iterative Generation Distorts Information

arXiv: https://arxiv.org/abs/2502.20258 · HTML: https://mlsanity.com/paper/2502.20258/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 46 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Builds on (most cited first, 27 of 27)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [The Curse of Recursion: Training on Generated Data Makes Models Forget](https://mlsanity.com/paper/2305.17493/) (2023)
- [FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios](https://mlsanity.com/paper/2307.13528/) (2023)
- [Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View](https://mlsanity.com/paper/2310.02124/) (2023)
- [BookSum: A Collection of Datasets for Long-form Narrative Summarization](https://mlsanity.com/paper/2105.08209/) (2021)
- [A Tale of Tails: Model Collapse as a Change of Scaling Laws](https://mlsanity.com/paper/2402.07043/) (2024)
- [Improving Multi-Agent Debate with Sparse Communication Topology](https://mlsanity.com/paper/2406.11776/) (2024)
- [The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text](https://mlsanity.com/paper/2311.09807/) (2023)
- [LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction](https://mlsanity.com/paper/2312.12343/) (2023)
- [Let Models Speak Ciphers: Multiagent Debate through Embeddings](https://mlsanity.com/paper/2310.06272/) (2023)
- [Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores](https://mlsanity.com/paper/2403.00553/) (2024)
- [When Does Unsupervised Machine Translation Work?](https://mlsanity.com/paper/2004.05516/) (2020)
- [AI and the Problem of Knowledge Collapse](https://mlsanity.com/paper/2404.03502/) (2024)
- [Towards Theoretical Understandings of Self-Consuming Generative Models](https://mlsanity.com/paper/2402.11778/) (2024)
- [OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs](https://mlsanity.com/paper/2408.11832/) (2024)
- [Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?](https://mlsanity.com/paper/2304.01002/) (2023)
- [Evaluating Distributional Distortion in Neural Language Modeling](https://mlsanity.com/paper/2203.12788/) (2022)
- [Tracking the perspectives of interacting language models](https://mlsanity.com/paper/2406.11938/) (2024)
- [To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation](https://mlsanity.com/paper/2401.01419/) (2024)
- [The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translation](https://mlsanity.com/paper/2403.18031/) (2024)

## Built on by (most cited first, 12 of 12)

- [Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text](https://mlsanity.com/paper/2506.14012/) (2025)
- [Wikipedia in the Era of LLMs: Evolution and Risks](https://mlsanity.com/paper/2503.02879/) (2025)
- [Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution](https://mlsanity.com/paper/2606.05408/) (2026)
- [Another Turn, Better Output? A Turn-Wise Analysis of Iterative LLM Prompting](https://mlsanity.com/paper/2509.06770/) (2025)
- [Markovian Generation Chains in Large Language Models](https://mlsanity.com/paper/2603.11228/) (2026)
- [When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis](https://mlsanity.com/paper/2606.29251/) (2026)
- [Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers](https://mlsanity.com/paper/2603.25638/) (2026)
- [HawkesLLM: Semantic Uncertainty Propagation in Agentic Text Simulation](https://mlsanity.com/paper/2605.23043/) (2026)
- [From 'May' to 'Is': Certainty Distortion in Language Model Rewriting](https://mlsanity.com/paper/2606.07951/) (2026)
- [Faithful, Not Corrective: Model Capability Governs Message-Format Effects in Multi-Hop Agent Relays](https://mlsanity.com/paper/2607.09678/) (2026)
- [Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration](https://mlsanity.com/paper/2608.11195/) (2026)
- [If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs](https://mlsanity.com/paper/2609.10123/) (2026)

## Abstract (arXiv)

As large language models are increasingly responsible for online content, concerns arise about the impact of repeatedly processing their own outputs. Inspired by the "broken telephone" effect in chained human communication, this study investigates whether LLMs similarly distort information through iterative generation. Through translation-based experiments, we find that distortion accumulates over time, influenced by language choice and chain complexity. While degradation is inevitable, it can be mitigated through strategic prompting techniques. These findings contribute to discussions on the long-term effects of AI-mediated information propagation, raising important questions about the reliability of LLM-generated content in iterative workflows.