LLM反复改写文本会陷入周期性稳定状态，限制语言多样性。
Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing
- 用动力系统视角分析LLM迭代改写过程，发现其趋向周期性吸引子。
- 连续改写最终收敛至2周期循环，语言表达趋于固定模式。
- 即使增加随机性或更换提示/模型，该现象仍存在，揭示生成局限。
动力系统理论为分析迭代过程与时间演化提供了框架。在该框架中，重复变换可能导向稳定结构，即吸引子，包括不动点和极限环。将此视角应用于大语言模型（LLMs），其逐轮将输入文本映射为输出文本的特性，可为长期行为建模提供理论依据。连续改写是探索此类动态的有力测试平台，因其以语言差异重新表达相同语义。尽管预期LLM能在文本空间中探索多样化改写，但研究发现，连续改写最终收敛至稳定的周期状态，如2周期吸引子环，限制了语言多样性。这一现象归因于LLM的自我强化机制，即在迭代中持续偏好并放大某些文本形式。该规律在增加生成随机性或交替使用不同提示与模型时依然成立。这些发现揭示了LLM生成能力的内在约束，同时为研究其表达潜力提供了新的动力系统视角。
原文摘要 · Abstract (English)
Dynamical systems theory provides a framework for analyzing iterative processes and evolution over time. Within such systems, repetitive transformations can lead to stable configurations, known as attractors, including fixed points and limit cycles. Applying this perspective to large language models (LLMs), which iteratively map input text to output text, provides a principled approach to characterizing long-term behaviors. Successive paraphrasing serves as a compelling testbed for exploring such dynamics, as paraphrases re-express the same underlying meaning with linguistic variation. Although LLMs are expected to explore a diverse set of paraphrases in the text space, our study reveals that successive paraphrasing converges to stable periodic states, such as 2-period attractor cycles, limiting linguistic diversity. This phenomenon is attributed to the self-reinforcing nature of LLMs, as they iteratively favour and amplify certain textual forms over others. This pattern persists with increasing generation randomness or alternating prompts and LLMs. These findings underscore inherent constraints in LLM generative capability, while offering a novel dynamical systems perspective for studying their expressive potential.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。