@inproceedings{zhong-etal-2026-beyond-isolated,
title = "Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction",
author = "Zhong, Tianyun and
Mo, Guozhao and
Liu, Yanjiang and
Chen, Yihan and
Kong, Lingdi and
Chen, Xuanang and
Lu, Yaojie and
Lin, Hongyu and
ye, Shiwei and
Jiang, Shanshan and
Dong, Bin and
Sun, Le and
He, Ben and
Han, Xianpei",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.160/",
pages = "3545--3574",
ISBN = "979-8-89176-439-2",
abstract = "With the emergence of large language models (LLMs), there is an expectation that they can effectively extract structured information from complex, real-world documents. However, most LLMs generate paragraph-style answers that are chaotic, disorganized, and untraceable. To bridge this gap, we introduce the Arranged and Organized Extraction Benchmark (AOE), a new bilingual benchmark featuring long-form documents (171k tokens on average) designed to systematically evaluate the ability of LLMs to comprehend fragmented information and reconstruct it into an organized table. Unlike conventional text-to-table tasks, which rely on fixed schema and narrow domains, AOE includes 12 carefully designed tasks across four diverse domains, requiring models to generate context-specific schema tailored to varied input queries. In our experiments, we evaluated 12 open-source and proprietary LLMs. Even the most advanced models struggle significantly."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhong-etal-2026-beyond-isolated">
<titleInfo>
<title>Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianyun</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guozhao</namePart>
<namePart type="family">Mo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanjiang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yihan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingdi</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaojie</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiwei</namePart>
<namePart type="family">ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shanshan</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>With the emergence of large language models (LLMs), there is an expectation that they can effectively extract structured information from complex, real-world documents. However, most LLMs generate paragraph-style answers that are chaotic, disorganized, and untraceable. To bridge this gap, we introduce the Arranged and Organized Extraction Benchmark (AOE), a new bilingual benchmark featuring long-form documents (171k tokens on average) designed to systematically evaluate the ability of LLMs to comprehend fragmented information and reconstruct it into an organized table. Unlike conventional text-to-table tasks, which rely on fixed schema and narrow domains, AOE includes 12 carefully designed tasks across four diverse domains, requiring models to generate context-specific schema tailored to varied input queries. In our experiments, we evaluated 12 open-source and proprietary LLMs. Even the most advanced models struggle significantly.</abstract>
<identifier type="citekey">zhong-etal-2026-beyond-isolated</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.160/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>3545</start>
<end>3574</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction
%A Zhong, Tianyun
%A Mo, Guozhao
%A Liu, Yanjiang
%A Chen, Yihan
%A Kong, Lingdi
%A Chen, Xuanang
%A Lu, Yaojie
%A Lin, Hongyu
%A ye, Shiwei
%A Jiang, Shanshan
%A Dong, Bin
%A Sun, Le
%A He, Ben
%A Han, Xianpei
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F zhong-etal-2026-beyond-isolated
%X With the emergence of large language models (LLMs), there is an expectation that they can effectively extract structured information from complex, real-world documents. However, most LLMs generate paragraph-style answers that are chaotic, disorganized, and untraceable. To bridge this gap, we introduce the Arranged and Organized Extraction Benchmark (AOE), a new bilingual benchmark featuring long-form documents (171k tokens on average) designed to systematically evaluate the ability of LLMs to comprehend fragmented information and reconstruct it into an organized table. Unlike conventional text-to-table tasks, which rely on fixed schema and narrow domains, AOE includes 12 carefully designed tasks across four diverse domains, requiring models to generate context-specific schema tailored to varied input queries. In our experiments, we evaluated 12 open-source and proprietary LLMs. Even the most advanced models struggle significantly.
%U https://aclanthology.org/2026.aacl-long.160/
%P 3545-3574
Markdown (Informal)
[Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction](https://aclanthology.org/2026.aacl-long.160/) (Zhong et al., AACL-IJCNLP 2026)
ACL
- Tianyun Zhong, Guozhao Mo, Yanjiang Liu, Yihan Chen, Lingdi Kong, Xuanang Chen, Yaojie Lu, Hongyu Lin, Shiwei ye, Shanshan Jiang, Bin Dong, Le Sun, Ben He, and Xianpei Han. 2026. Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3545–3574, Hengqin, China. Association for Computational Linguistics.