@inproceedings{fujitake-2024-layoutllm,
title = "{L}ayout{LLM}: Large Language Model Instruction Tuning for Visually Rich Document Understanding",
author = "Fujitake, Masato",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.892",
pages = "10219--10224",
abstract = "This paper proposes LayoutLLM, a more flexible document analysis method for understanding imaged documents. Visually Rich Document Understanding tasks, such as document image classification and information extraction, have gained significant attention due to their importance. Existing methods have been developed to enhance document comprehension by incorporating pre-training awareness of images, text, and layout structure. However, these methods require fine-tuning for each task and dataset, and the models are expensive to train and operate. To overcome this limitation, we propose a new LayoutLLM that integrates these with large-scale language models (LLMs). By leveraging the strengths of existing research in document image understanding and LLMs{'} superior language understanding capabilities, the proposed model, fine-tuned with multimodal instruction datasets, performs an understanding of document images in a single model. Our experiments demonstrate improvement over the baseline model in various document analysis tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fujitake-2024-layoutllm">
<titleInfo>
<title>LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masato</namePart>
<namePart type="family">Fujitake</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper proposes LayoutLLM, a more flexible document analysis method for understanding imaged documents. Visually Rich Document Understanding tasks, such as document image classification and information extraction, have gained significant attention due to their importance. Existing methods have been developed to enhance document comprehension by incorporating pre-training awareness of images, text, and layout structure. However, these methods require fine-tuning for each task and dataset, and the models are expensive to train and operate. To overcome this limitation, we propose a new LayoutLLM that integrates these with large-scale language models (LLMs). By leveraging the strengths of existing research in document image understanding and LLMs’ superior language understanding capabilities, the proposed model, fine-tuned with multimodal instruction datasets, performs an understanding of document images in a single model. Our experiments demonstrate improvement over the baseline model in various document analysis tasks.</abstract>
<identifier type="citekey">fujitake-2024-layoutllm</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.892</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10219</start>
<end>10224</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding
%A Fujitake, Masato
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F fujitake-2024-layoutllm
%X This paper proposes LayoutLLM, a more flexible document analysis method for understanding imaged documents. Visually Rich Document Understanding tasks, such as document image classification and information extraction, have gained significant attention due to their importance. Existing methods have been developed to enhance document comprehension by incorporating pre-training awareness of images, text, and layout structure. However, these methods require fine-tuning for each task and dataset, and the models are expensive to train and operate. To overcome this limitation, we propose a new LayoutLLM that integrates these with large-scale language models (LLMs). By leveraging the strengths of existing research in document image understanding and LLMs’ superior language understanding capabilities, the proposed model, fine-tuned with multimodal instruction datasets, performs an understanding of document images in a single model. Our experiments demonstrate improvement over the baseline model in various document analysis tasks.
%U https://aclanthology.org/2024.lrec-main.892
%P 10219-10224
Markdown (Informal)
[LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding](https://aclanthology.org/2024.lrec-main.892) (Fujitake, LREC-COLING 2024)
ACL