arXiv Open Access 2026

Can LLMs Track Their Output Length? A Dynamic Feedback Mechanism for Precise Length Regulation

Meiman Xiao Ante Wang Qingguo Hu Zhongjian Miao Huangjun Shen +3 lainnya
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (8)

M

Meiman Xiao

A

Ante Wang

Q

Qingguo Hu

Z

Zhongjian Miao

H

Huangjun Shen

L

Longyue Wang

W

Weihua Luo

J

Jinsong Su

Format Sitasi

Xiao, M., Wang, A., Hu, Q., Miao, Z., Shen, H., Wang, L. et al. (2026). Can LLMs Track Their Output Length? A Dynamic Feedback Mechanism for Precise Length Regulation. https://arxiv.org/abs/2601.01768

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2026
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓