Shifting Long-Context LLMs Research from Input to Output
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917947330527232 |
|---|---|
| author | Wu, Yuhao Bai, Yushi Hu, Zhiqing Tu, Shangqing Hee, Ming Shan Li, Juanzi Lee, Roy Ka-Wei |
| author_facet | Wu, Yuhao Bai, Yushi Hu, Zhiqing Tu, Shangqing Hee, Ming Shan Li, Juanzi Lee, Roy Ka-Wei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04723 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Shifting Long-Context LLMs Research from Input to Output Wu, Yuhao Bai, Yushi Hu, Zhiqing Tu, Shangqing Hee, Ming Shan Li, Juanzi Lee, Roy Ka-Wei Computation and Language Artificial Intelligence 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. |
| title | Shifting Long-Context LLMs Research from Input to Output |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.04723 |