Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2601.01768 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909983091720192 |
|---|---|
| author | Xiao, Meiman Wang, Ante Hu, Qingguo Miao, Zhongjian Shen, Huangjun Wang, Longyue Luo, Weihua Su, Jinsong |
| author_facet | Xiao, Meiman Wang, Ante Hu, Qingguo Miao, Zhongjian Shen, Huangjun Wang, Longyue Luo, Weihua Su, Jinsong |
| contents | Precisely controlling the length of generated text is a common requirement in real-world applications. However, despite significant advancements in following human instructions, Large Language Models (LLMs) still struggle with this task. In this work, we demonstrate that LLMs often fail to accurately measure their response lengths, leading to poor adherence to length constraints. To address this issue, we propose a novel length regulation approach that incorporates dynamic length feedback during generation, enabling adaptive adjustments to meet target lengths. Experiments on summarization and biography tasks show our training-free approach significantly improves precision in achieving target token, word, or sentence counts without compromising quality. Additionally, we demonstrate that further supervised fine-tuning allows our method to generalize effectively to broader text-generation tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01768 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Can LLMs Track Their Output Length? A Dynamic Feedback Mechanism for Precise Length Regulation Xiao, Meiman Wang, Ante Hu, Qingguo Miao, Zhongjian Shen, Huangjun Wang, Longyue Luo, Weihua Su, Jinsong Computation and Language Precisely controlling the length of generated text is a common requirement in real-world applications. However, despite significant advancements in following human instructions, Large Language Models (LLMs) still struggle with this task. In this work, we demonstrate that LLMs often fail to accurately measure their response lengths, leading to poor adherence to length constraints. To address this issue, we propose a novel length regulation approach that incorporates dynamic length feedback during generation, enabling adaptive adjustments to meet target lengths. Experiments on summarization and biography tasks show our training-free approach significantly improves precision in achieving target token, word, or sentence counts without compromising quality. Additionally, we demonstrate that further supervised fine-tuning allows our method to generalize effectively to broader text-generation tasks. |
| title | Can LLMs Track Their Output Length? A Dynamic Feedback Mechanism for Precise Length Regulation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.01768 |