Recent advancements in long-context Large Language Models (LLMs) have primarily concentrated on processing extended input contexts, resulting in significant strides in long-context comprehension. However, the equally critical aspect of generating long-form outputs has received comparatively less attention. This paper advocates for a paradigm shift in NLP research toward addressing the challenges of long-output generation. Tasks such as novel writing, long-term planning, and complex reasoning require models to understand extensive contexts and produce coherent, contextually rich, and logically consistent extended text. These demands highlight a critical gap in current LLM capabilities. We underscore the importance of this under-explored domain and call for focused efforts to develop foundational LLMs tailored for generating high-quality, long-form outputs, which hold immense potential for real-world applications.
@article{arxiv.2503.04723,
title = {Shifting Long-Context LLMs Research from Input to Output},
author = {Yuhao Wu and Yushi Bai and Zhiqing Hu and Shangqing Tu and Ming Shan Hee and Juanzi Li and Roy Ka-Wei Lee},
journal= {arXiv preprint arXiv:2503.04723},
year = {2025}
}