<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peng-etal-2026-nest">
    <titleInfo>
        <title>NEST: A Benchmark for Explicit Structural Parsing on Native Empty Templates</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chen</namePart>
        <namePart type="family">Peng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tianci</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hongye</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiayi</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kangdi</namePart>
        <namePart type="family">Hao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yiping</namePart>
        <namePart type="family">Song</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Certain document automation scenarios, such as intelligent form infilling and privacy-strict parsing, require models to comprehend unpopulated templates. Yet existing benchmarks mainly use content-filled tables, leaving the template side of document understanding under-evaluated. To bridge this gap, we introduce NEST, a benchmark of 828 Native Empty Structural Templates from real-world, born-digital forms. NEST removes filled content while preserving complex hierarchical layouts and guided selection options in authentic administrative workflows. Through Structural Schema Parsing, Cell-Header Alignment, and Generative Infilling, NEST directly evaluates structural reasoning without content-based shortcuts. Experiments reveal a clear template–instance gap: state-of-the-art LLMs drop by 9.5 percentage points on average when evaluated on unpopulated templates rather than populated instances. We further show that Generative Infilling is a data-efficient tuning signal for template completion, raising infilling accuracy by 16.37 percentage points and the three-task average by 8.19 percentage points with only 662 (80%) training templates. NEST thus provides a benchmark for measuring template-level understanding and highlights a data-efficient route for improving template completion. The code, data, and results for this paper are available at https://github.com/cpeng-research/NEST-Benchmark.</abstract>
    <identifier type="citekey">peng-etal-2026-nest</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1010/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>23248</start>
            <end>23263</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T NEST: A Benchmark for Explicit Structural Parsing on Native Empty Templates
%A Peng, Chen
%A He, Tianci
%A Chen, Hongye
%A Huang, Jiayi
%A Hao, Kangdi
%A Song, Yiping
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F peng-etal-2026-nest
%X Certain document automation scenarios, such as intelligent form infilling and privacy-strict parsing, require models to comprehend unpopulated templates. Yet existing benchmarks mainly use content-filled tables, leaving the template side of document understanding under-evaluated. To bridge this gap, we introduce NEST, a benchmark of 828 Native Empty Structural Templates from real-world, born-digital forms. NEST removes filled content while preserving complex hierarchical layouts and guided selection options in authentic administrative workflows. Through Structural Schema Parsing, Cell-Header Alignment, and Generative Infilling, NEST directly evaluates structural reasoning without content-based shortcuts. Experiments reveal a clear template–instance gap: state-of-the-art LLMs drop by 9.5 percentage points on average when evaluated on unpopulated templates rather than populated instances. We further show that Generative Infilling is a data-efficient tuning signal for template completion, raising infilling accuracy by 16.37 percentage points and the three-task average by 8.19 percentage points with only 662 (80%) training templates. NEST thus provides a benchmark for measuring template-level understanding and highlights a data-efficient route for improving template completion. The code, data, and results for this paper are available at https://github.com/cpeng-research/NEST-Benchmark.
%U https://aclanthology.org/2026.emnlp-main.1010/
%P 23248-23263

Markdown (Informal)

[NEST: A Benchmark for Explicit Structural Parsing on Native Empty Templates](https://aclanthology.org/2026.emnlp-main.1010/) (Peng et al., EMNLP 2026)

• NEST: A Benchmark for Explicit Structural Parsing on Native Empty Templates (Peng et al., EMNLP 2026)

ACL

• Chen Peng, Tianci He, Hongye Chen, Jiayi Huang, Kangdi Hao, and Yiping Song. 2026. NEST: A Benchmark for Explicit Structural Parsing on Native Empty Templates. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 23248–23263, Budapest, Hungary. Association for Computational Linguistics.