LLM as a Broken Telephone: Iterative Generation Distorts Information
This addresses concerns about the reliability of LLM-generated content in iterative workflows, such as online content creation, but is incremental in nature.
The study investigated whether large language models distort information through iterative generation, finding that distortion accumulates over time but can be mitigated with strategic prompting.
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.