LLM as a Broken Telephone: Iterative Generation Distorts Information
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908539114487808 |
|---|---|
| author | Mohamed, Amr Geng, Mingmeng Vazirgiannis, Michalis Shang, Guokan |
| author_facet | Mohamed, Amr Geng, Mingmeng Vazirgiannis, Michalis Shang, Guokan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20258 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM as a Broken Telephone: Iterative Generation Distorts Information Mohamed, Amr Geng, Mingmeng Vazirgiannis, Michalis Shang, Guokan Computation and Language Artificial Intelligence 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. |
| title | LLM as a Broken Telephone: Iterative Generation Distorts Information |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.20258 |