Ruler: A Model-Agnostic Method to Control Generated Length for Large Language Models

TL;DR

This paper introduces Ruler, a model-agnostic method that improves large language models' ability to generate responses of specified lengths by using Meta Length Tokens, enhancing control and versatility.

Contribution

The paper proposes Ruler, a novel, model-agnostic approach utilizing Meta Length Tokens to better control response length in large language models, including automatic length constraint generation.

Findings

Ruler significantly improves length control accuracy across various LLMs.

It achieves an average gain of 27.97 on Precise Match and 29.57 on Flexible Match metrics.

Extensive experiments validate Ruler's effectiveness and generalization.

Abstract

The instruction-following ability of large language models enables humans to interact with AI agents in a natural way. However, when required to generate responses of a specific length, large language models often struggle to meet users' needs due to their inherent difficulty in accurately perceiving numerical constraints. To explore the ability of large language models to control the length of generated responses, we propose the Target Length Generation Task (TLG) and design two metrics, Precise Match (PM) and Flexible Match (FM) to evaluate the model's performance in adhering to specified response lengths. Furthermore, we introduce a novel, model-agnostic approach called Ruler, which employs Meta Length Tokens (MLTs) to enhance the instruction-following ability of large language models under length-constrained instructions. Specifically, Ruler equips LLMs with the ability to generate responses of a specified length based on length constraints within the instructions. Moreover, Ruler can automatically generate appropriate MLT when length constraints are not explicitly provided, demonstrating excellent versatility and generalization. Comprehensive experiments show the effectiveness of Ruler across different LLMs on Target Length Generation Task, e.g., at All Level 27.97 average gain on PM, 29.57 average gain on FM. In addition, we conduct extensive ablation experiments to further substantiate the efficacy and generalization of Ruler. Our code and data is available at https://github.com/Geaming2002/Ruler.