Long context is an important topic in Natural Language Processing (NLP), running through the development of NLP architectures, and offers immense opportunities for Large Language Models (LLMs) giving LLMs the lifelong learning potential akin to humans. Unfortunately, the pursuit of a long context is accompanied by numerous obstacles. Nevertheless, long context remains a core competitive advantage for LLMs. In the past two years, the context length of LLMs has achieved a breakthrough extension to millions of tokens. Moreover, the research on long-context LLMs has expanded from length extrapolation to a comprehensive focus on architecture, infrastructure, training, and evaluation technologies.Inspired by the symphonic poem, Thus Spake Zarathustra, we draw an analogy between the journey of extending the context of LLM and the attempts of humans to transcend its mortality. In this survey, We will illustrate how LLM struggles between the tremendous need for a longer context and its equal need to accept the fact that it is ultimately finite. To achieve this, we give a global picture of the lifecycle of long-context LLMs from four perspectives: architecture, infrastructure, training, and evaluation, showcasing the full spectrum of long-context technologies. At the end of this survey, we will present 10 unanswered questions currently faced by long-context LLMs. We hope this survey can serve as a systematic introduction to the research on long-context LLMs.
View on arXiv@article{liu2025_2502.17129,
title={ Thus Spake Long-Context Large Language Model },
author={ Xiaoran Liu and Ruixiao Li and Mianqiu Huang and Zhigeng Liu and Yuerong Song and Qipeng Guo and Siyang He and Qiqi Wang and Linlin Li and Qun Liu and Yaqian Zhou and Xuanjing Huang and Xipeng Qiu },
journal={arXiv preprint arXiv:2502.17129},
year={ 2025 }
}