ACL Findings2026
DcLM: Output Length Control of Large Language Models via Dynamic Length Markers
Abstract
Length-controllable text generation (LCTG) is essential for tasks like text summarization and report generation. However, large language models (LLMs) have limited awareness of output length, so precise control over the length of generated text remains a significant challenge. Most existing methods focus on promptbased frameworks, position encoding, and reinforcement learning for model training. These approaches may affect semantic quality, and struggle to maintain consistent length control across different models and tasks. In this paper, we propose DcLM, a model-agnostic approach that introduces dynamic length markers to guide length-controllable outputs. During training, the model leverages these markers as in-context information, without learning to generate them. At inference time, an external word counter and injected length information guide the model to produce outputs of accurate lengths. We evaluate our method across multiple datasets, and the experimental results demonstrate that DcLM significantly reduces length deviation, showcasing its robust generalization ability across various length scales and tasks.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- TruthfulQA: Measuring How Models Mimic Human Falsehoods cites Measuring Massive Multitask Language Understanding
- Hansel: Output Length Controlling Framework for Large Language Models cites G-Eval: NLG Evaluation using Gpt-4 with Better Human Alignment
Builds on13
- Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou et al.ICLR 2021 · 7,905 citations
- TruthfulQA: Measuring How Models Mimic Human FalsehoodsStephanie Lin, Jacob Hilton, Owain EvansACL 2022 · 3,228 citations
- G-Eval: NLG Evaluation using Gpt-4 with Better Human AlignmentYang Liu, Dan Iter, Yichong Xu, Shuohang Wang et al.EMNLP 2023 · 549 citations
- Prompt-Based Length Controlled Generation with Multiple Control TypesRenlong Jie, Xiaojun Meng, Lifeng Shang, Xin Jiang et al.ACL Findings 2024 · 4 citations
- Hansel: Output Length Controlling Framework for Large Language ModelsSeoha Song, Junhyun Lee, Hyeonmok KoAAAI 2025 · 2 citations
Related papers
- Ruler: A Model-Agnostic Method to Control Generated Length for Large Language ModelsJiaming Li, Lei Zhang, Yunshui Li, Ziqiang Liu et al.EMNLP Findings 2024 · 1 citation
- From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGenPeiwen Yuan, Chuyi Tan, Shaoxiong Feng, Yiwei Li et al.ACL 2025 · 2 citations
- LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language ModelsWei Zhang, Lintong Du, yuanhe zhang, Zhenhong Zhou et al.ICML 2026
- Length Control in Abstractive Summarization by Pretraining Information SelectionYizhu Liu, Qi Jia, Kenny Q. ZhuACL 2022 · 39 citations
- PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional AwarenessNoah Wang, Feiyu Duan, Yibo Zhang, Wangchunshu Zhou et al.EMNLP Findings 2024 · 1 citation
