Plan-and-Write: Structure-Guided Length Control for LLMs without Model Retraining
By: Adewale Akinfaderin, Shreyas Subramanian, Akarsha Sehwag
Potential Business Impact:
Makes AI write exactly the right amount of words.
Length control in Large Language Models (LLMs) is a crucial but under-addressed challenge, with applications ranging from voice interfaces requiring concise responses to research summaries needing comprehensive outputs. Current approaches to length control, including Regularized DPO, Length-Instruction Fine Tuning, and tool-augmented methods, typically require expensive model retraining or complex inference-time tooling. This paper presents a prompt engineering methodology that enables precise length control without model retraining. Our structure-guided approach implements deliberate planning and word counting mechanisms within the prompt, encouraging the model to carefully track and adhere to specified length constraints. Comprehensive evaluations across six state-of-the-art LLMs demonstrate that our method significantly improves length fidelity for several models compared to standard prompting when applied to document summarization tasks, particularly for shorter-to-medium length constraints. The proposed technique shows varying benefits across different model architectures, with some models demonstrating up to 37.6% improvement in length adherence. Quality evaluations further reveal that our approach maintains or enhances overall output quality compared to standard prompting techniques. Our approach provides an immediately deployable solution for applications requiring precise length control, particularly valuable for production environments where model retraining is impractical or cost-prohibitive.
Similar Papers
Prompt-Based One-Shot Exact Length-Controlled Generation with LLMs
Computation and Language
Makes AI write exactly the right number of words.
How Instruction-Tuning Imparts Length Control: A Cross-Lingual Mechanistic Analysis
Computation and Language
Makes AI write exactly how long you want.
LLMs for LLMs: A Structured Prompting Methodology for Long Legal Documents
Artificial Intelligence
Helps lawyers find facts in long legal papers.