AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

LayoutPrompter: Awaken the Design Ability of Large Language Models

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

NeurIPS 2023 · Large language models › Instruction and fine-tuning · approach: Efficient LLM fine-tuning systems · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
serialize output layout as HTML instead of plain sequence (ablation)LayoutPrompter · RICO Gen-TFID: 7.009 -> 3.233Improved
add dynamic exemplar selection instead of random exemplars (ablation)LayoutPrompter · RICO Gen-TFID: 8.154 -> 3.233Improved
add dynamic exemplar selection instead of random exemplars (ablation)LayoutPrompter · RICO Gen-RFID: 14.177 -> 5.178Improved
add dynamic exemplar selection instead of random exemplars (ablation)LayoutPrompter · RICO Gen-TAlign.: 0.053 -> 0.109Hurt
add layout ranker instead of random pick (ablation)LayoutPrompter · RICO Gen-TmIoU: 0.367 -> 0.429Improved
add layout ranker instead of random pick (ablation)LayoutPrompter · RICO CompletionFID: 11.194 -> 7.318Improved
add layout ranker instead of random pick (ablation)LayoutPrompter · RICO Gen-RVio. %: 6.54 -> 10.58Hurt
increase number of exemplars from 1 to 10 (ablation)LayoutPrompter · RICO Gen-TFID: 5.007 -> 3.523Improved
LLM in-context learning vs trained LayoutFormer++ with 500 training samples (ablation)LayoutPrompter · RICO Gen-TFID: 92.643 -> 7.201Improved
LLM in-context learning vs trained LayoutFormer++ with full training setLayoutPrompter · RICO Gen-TSFID: 0.757 -> 1.458Hurt
LayoutPrompter vs DS-GAN on content-aware generationLayoutPrompter · PosterLayoutUnd_s: 0.4320 -> 0.8802Improved
LayoutPrompter vs parse-then-place on text-to-layoutLayoutPrompter · WebUImIoU: 0.6841 -> 0.3190Hurt

Later papers that compared with this method

1 later accepted paper reports LayoutPrompter as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy