<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-um">
    <titleInfo>
        <title>Um, Actually: Timely and Calibrated Fact-Checking with DIVER</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Senyi</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tasnim</namePart>
        <namePart type="family">Kabir</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jordan</namePart>
        <namePart type="family">Boyd-Graber</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>Fact verification pipelines are often unrealistic: they assume full-input access, operate on isolated atomic claims, and overlook the central question of when a system should act under partial evidence. We introduce DIVER (Deliberative and Iterative fact VERification), an LLM-based framework for calibrated incremental fact-checking. DIVER incrementally extracts verifiable atomic claims from progressively revealed input, retrieves and refines evidence through iterative web search, and triggers a correction as soon as a claim is reliably refuted; if no such trigger occurs, it performs a passage-level revision over the full input to recover missed errors. Across standard fact-checking benchmarks, DIVER outperforms strong LLM-based verification pipelines, with especially large gains on retrieval-intensive settings. We further introduce UmActually, a real-world benchmark built from the Internet game Um, Actually, to evaluate not only whether a system finds an error, but whether it does so at the right time. On UmActually, DIVER reports the strongest end-to-end results while typically buzzing close to the earliest valid decision point, supporting its effectiveness for calibrated incremental fact-checking.</abstract>
    <identifier type="citekey">zhang-etal-2026-um</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.855/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>18092</start>
            <end>18106</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Um, Actually: Timely and Calibrated Fact-Checking with DIVER
%A Zhang, Senyi
%A Kabir, Tasnim
%A Boyd-Graber, Jordan
%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 zhang-etal-2026-um
%X Fact verification pipelines are often unrealistic: they assume full-input access, operate on isolated atomic claims, and overlook the central question of when a system should act under partial evidence. We introduce DIVER (Deliberative and Iterative fact VERification), an LLM-based framework for calibrated incremental fact-checking. DIVER incrementally extracts verifiable atomic claims from progressively revealed input, retrieves and refines evidence through iterative web search, and triggers a correction as soon as a claim is reliably refuted; if no such trigger occurs, it performs a passage-level revision over the full input to recover missed errors. Across standard fact-checking benchmarks, DIVER outperforms strong LLM-based verification pipelines, with especially large gains on retrieval-intensive settings. We further introduce UmActually, a real-world benchmark built from the Internet game Um, Actually, to evaluate not only whether a system finds an error, but whether it does so at the right time. On UmActually, DIVER reports the strongest end-to-end results while typically buzzing close to the earliest valid decision point, supporting its effectiveness for calibrated incremental fact-checking.
%U https://aclanthology.org/2026.findings-emnlp.855/
%P 18092-18106

Markdown (Informal)

[Um, Actually: Timely and Calibrated Fact-Checking with DIVER](https://aclanthology.org/2026.findings-emnlp.855/) (Zhang et al., Findings 2026)

• Um, Actually: Timely and Calibrated Fact-Checking with DIVER (Zhang et al., Findings 2026)

ACL

• Senyi Zhang, Tasnim Kabir, and Jordan Boyd-Graber. 2026. Um, Actually: Timely and Calibrated Fact-Checking with DIVER. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 18092–18106, Budapest, Hungary. Association for Computational Linguistics.