Pre-trained large language models (LLMs) have powerful capabilities for generating creative natural text. Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems. Motivated by the common collective and directionality of text generation and evolution, this paper illustrates the parallels between LLMs and EAs, which includes multiple one-to-one key characteristics: token representation and individual representation, position encoding and fitness shaping, position embedding and selection, Transformers block and reproduction, and model training and parameter adaptation. By examining these parallels, we analyze existing interdisciplinary research, with a specific focus on evolutionary fine-tuning and LLM-enhanced EAs. Drawing from these insights, valuable future directions are presented for advancing the integration of LLMs and EAs, while highlighting key challenges along the way. These parallels not only reveal the evolution mechanism behind LLMs but also facilitate the development of evolved artificial agents that approach or surpass biological organisms.

翻译：预训练大语言模型（LLMs）具备生成创造性自然文本的强大能力。进化算法（EAs）能够为复杂现实问题发现多样化解决方案。受文本生成与进化过程共有的群体性与方向性启发，本文阐述了大语言模型与进化算法之间的对应关系，其中包括多组一一对应的关键特征：词元表示与个体表示、位置编码与适应度塑形、位置嵌入与选择、Transformer模块与繁殖，以及模型训练与参数适配。通过审视这些对应关系，我们分析了现有的跨学科研究，特别聚焦于进化微调与LLM增强的进化算法。基于这些见解，本文提出了推动大语言模型与进化算法融合的未来研究方向，并指出了该过程中的关键挑战。这些对应关系不仅揭示了大语言模型背后的进化机制，也将促进开发能够接近或超越生物有机体的进化人工智能体。