Skip to yearly menu bar Skip to main content


LayoutPrompter: Awaken the Design Ability of Large Language Models

Jiawei Lin · Jiaqi Guo · Shizhao Sun · Zijiang Yang · Jian-Guang Lou · Dongmei Zhang

Great Hall & Hall B1+B2 (level 1) #304
[ ]
[ Paper [ Poster [ OpenReview
Tue 12 Dec 8:45 a.m. PST — 10:45 a.m. PST


Conditional graphic layout generation, which automatically maps user constraints to high-quality layouts, has attracted widespread attention today. Although recent works have achieved promising performance, the lack of versatility and data efficiency hinders their practical applications. In this work, we propose LayoutPrompter, which leverages large language models (LLMs) to address the above problems through in-context learning. LayoutPrompter is made up of three key components, namely input-output serialization, dynamic exemplar selection and layout ranking. Specifically, the input-output serialization component meticulously designs the input and output formats for each layout generation task. Dynamic exemplar selection is responsible for selecting the most helpful prompting exemplars for a given input. And a layout ranker is used to pick the highest quality layout from multiple outputs of LLMs. We conduct experiments on all existing layout generation tasks using four public datasets. Despite the simplicity of our approach, experimental results show that LayoutPrompter can compete with or even outperform state-of-the-art approaches on these tasks without any model training or fine-tuning. This demonstrates the effectiveness of this versatile and training-free approach. In addition, the ablation studies show that LayoutPrompter is significantly superior to the training-based baseline in a low-data regime, further indicating the data efficiency of LayoutPrompter. Our project is available at

Chat is not available.