@inproceedings{liao-wang-2026-retrieve,
title = "Retrieve Few, Verify Many: Segment-Level Evidence Reuse for Long-Form Factuality Assessment",
author = "Liao, Junjie and
Wang, Yuxia",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1584/",
pages = "33740--33753",
ISBN = "979-8-89176-462-0",
abstract = "Existing methods for evaluating the factuality of long-form LLM responses decompose text into atomic claims and verify each independently, retrieving evidence separately for every claim. This atom-independence assumption causes substantial retrieval redundancy, because adjacent claims in coherent text often draw from overlapping sources, a property we term semantic locality. We propose SegmentFact, a deterministic factuality assessor that partitions responses into semantic segments, extracts claims within each segment{'}s local context, and propagates retrieved evidence forward through a shared pool. Experiments on multiple benchmarks show that SegmentFact significantly reduces retrieval calls while maintaining accuracy comparable to existing detections."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liao-wang-2026-retrieve">
<titleInfo>
<title>Retrieve Few, Verify Many: Segment-Level Evidence Reuse for Long-Form Factuality Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junjie</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxia</namePart>
<namePart type="family">Wang</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Existing methods for evaluating the factuality of long-form LLM responses decompose text into atomic claims and verify each independently, retrieving evidence separately for every claim. This atom-independence assumption causes substantial retrieval redundancy, because adjacent claims in coherent text often draw from overlapping sources, a property we term semantic locality. We propose SegmentFact, a deterministic factuality assessor that partitions responses into semantic segments, extracts claims within each segment’s local context, and propagates retrieved evidence forward through a shared pool. Experiments on multiple benchmarks show that SegmentFact significantly reduces retrieval calls while maintaining accuracy comparable to existing detections.</abstract>
<identifier type="citekey">liao-wang-2026-retrieve</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1584/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>33740</start>
<end>33753</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retrieve Few, Verify Many: Segment-Level Evidence Reuse for Long-Form Factuality Assessment
%A Liao, Junjie
%A Wang, Yuxia
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F liao-wang-2026-retrieve
%X Existing methods for evaluating the factuality of long-form LLM responses decompose text into atomic claims and verify each independently, retrieving evidence separately for every claim. This atom-independence assumption causes substantial retrieval redundancy, because adjacent claims in coherent text often draw from overlapping sources, a property we term semantic locality. We propose SegmentFact, a deterministic factuality assessor that partitions responses into semantic segments, extracts claims within each segment’s local context, and propagates retrieved evidence forward through a shared pool. Experiments on multiple benchmarks show that SegmentFact significantly reduces retrieval calls while maintaining accuracy comparable to existing detections.
%U https://aclanthology.org/2026.findings-emnlp.1584/
%P 33740-33753
Markdown (Informal)
[Retrieve Few, Verify Many: Segment-Level Evidence Reuse for Long-Form Factuality Assessment](https://aclanthology.org/2026.findings-emnlp.1584/) (Liao & Wang, Findings 2026)
ACL