LLM作為斷線電話：迭代生成導致信息失真

LLM as a Broken Telephone: Iterative Generation Distorts Information

February 27, 2025

作者: Amr Mohamed, Mingmeng Geng, Michalis Vazirgiannis, Guokan Shang

cs.AI

摘要

隨著大型語言模型日益負責線上內容的生成，人們開始擔憂其反覆處理自身輸出所帶來的影響。本研究受到人類連鎖溝通中「傳話失真」效應的啟發，探討大型語言模型是否會通過迭代生成過程同樣造成信息失真。通過基於翻譯的實驗，我們發現失真會隨著時間累積，並受到語言選擇和鏈條複雜度的影響。雖然信息退化不可避免，但可以通過策略性的提示技術來緩解。這些發現為討論人工智慧中介信息傳播的長期效應提供了新的見解，並引發了關於迭代工作流程中大型語言模型生成內容可靠性的重要問題。

English

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.