<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pottanigari-etal-2026-splitting">
    <titleInfo>
        <title>Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nikhil</namePart>
        <namePart type="given">Reddy</namePart>
        <namePart type="family">Pottanigari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sepideh</namePart>
        <namePart type="family">Kharaghani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Saverio</namePart>
        <namePart type="family">Vadacchino</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alejandro</namePart>
        <namePart type="family">Posada</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ying</namePart>
        <namePart type="family">Zhang</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>The Proceedings of Workshop on Document Intelligence and Understanding</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Santosh</namePart>
            <namePart type="family">T.Y.S.S.</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Amit</namePart>
            <namePart type="family">Agarwal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Gupta</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yova</namePart>
            <namePart type="family">Kementchedjhieva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aparna</namePart>
            <namePart type="family">Garimella</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yufang</namePart>
            <namePart type="family">Hou</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">979-8-89176-477-4</identifier>
    </relatedItem>
    <abstract>Scanned mail, uploaded PDFs, and consolidated attachments often arrive as page streams that must be split into individual documents before downstream classification, extraction, or routing. Zero-shot large language models can detect document boundaries without task-specific training, but standard Page Classification (PC) and Boundary Decision (BD) formulations resolve only one boundary per model call. We introduce Multi-Split Boundary Decision (MSBD), which predicts multiple boundaries within a page window in a single call, reducing the number of inference requests. We evaluate MSBD across multiple language models, document collections, input modalities, and window sizes. The results reveal a model- and corpus-dependent operating range in which MSBD preserves strong segmentation accuracy while substantially improving inference efficiency, followed by a sharp decline at larger windows. MSBD provided the strongest overall accuracy–efficiency trade-off, while large windows expose distinct over- and under-segmentation behavior across models. These findings show that multi-boundary prediction can make zero-shot page stream segmentation more efficient when the window size is selected for the target corpus.</abstract>
    <identifier type="citekey">pottanigari-etal-2026-splitting</identifier>
    <location>
        <url>https://aclanthology.org/2026.docinsights-1.3/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>30</start>
            <end>45</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation
%A Pottanigari, Nikhil Reddy
%A Kharaghani, Sepideh
%A Vadacchino, Saverio
%A Posada, Alejandro
%A Zhang, Ying
%Y T.Y.S.S., Santosh
%Y Agarwal, Amit
%Y Gupta, Vivek
%Y Kementchedjhieva, Yova
%Y Garimella, Aparna
%Y Hou, Yufang
%S The Proceedings of Workshop on Document Intelligence and Understanding
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-477-4
%F pottanigari-etal-2026-splitting
%X Scanned mail, uploaded PDFs, and consolidated attachments often arrive as page streams that must be split into individual documents before downstream classification, extraction, or routing. Zero-shot large language models can detect document boundaries without task-specific training, but standard Page Classification (PC) and Boundary Decision (BD) formulations resolve only one boundary per model call. We introduce Multi-Split Boundary Decision (MSBD), which predicts multiple boundaries within a page window in a single call, reducing the number of inference requests. We evaluate MSBD across multiple language models, document collections, input modalities, and window sizes. The results reveal a model- and corpus-dependent operating range in which MSBD preserves strong segmentation accuracy while substantially improving inference efficiency, followed by a sharp decline at larger windows. MSBD provided the strongest overall accuracy–efficiency trade-off, while large windows expose distinct over- and under-segmentation behavior across models. These findings show that multi-boundary prediction can make zero-shot page stream segmentation more efficient when the window size is selected for the target corpus.
%U https://aclanthology.org/2026.docinsights-1.3/
%P 30-45

Markdown (Informal)

[Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation](https://aclanthology.org/2026.docinsights-1.3/) (Pottanigari et al., DocInsights 2026)

• Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation (Pottanigari et al., DocInsights 2026)

ACL

• Nikhil Reddy Pottanigari, Sepideh Kharaghani, Saverio Vadacchino, Alejandro Posada, and Ying Zhang. 2026. Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation. In The Proceedings of Workshop on Document Intelligence and Understanding, pages 30–45, Budapest, Hungary. Association for Computational Linguistics.