<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yotkova-etal-2026-correct">
    <titleInfo>
        <title>How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Elitsa</namePart>
        <namePart type="family">Yotkova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Violeta</namePart>
        <namePart type="family">Kastreva</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Petar</namePart>
        <namePart type="family">Velkov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hristo</namePart>
        <namePart type="family">Boyanov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dimitar</namePart>
        <namePart type="given">Iliyanov</namePart>
        <namePart type="family">Dimitrov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Preslav</namePart>
        <namePart type="family">Nakov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ivan</namePart>
        <namePart type="family">Koychev</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>Reliable evaluation of open-ended question answering remains a bottleneck for measuring answer correctness of modern LLMs. Unlike multiple-choice tasks, free-form answers may be correct in many surface forms and may fail in qualitatively different ways, including incompleteness, contradiction, overgeneration, and endorsement of false premises. Existing judgment-based and similarity-based metrics often collapse these distinctions. We address this gap with three reusable contributions. First, we introduce a semantic correctness taxonomy that assigns open-ended answers to eight ordered classes, separating verbose-but-correct answers from those contaminated by hallucinated content. Second, we release CAP-Correctness, an 8.8k-example benchmark spanning widely used QA datasets, and CAP-Statements, an 11k-example dataset for converting question-answer pairs into declarative statements for natural language inference (NLI) training and statement-based evaluation. Third, we introduce CAP (Context-Aware Precision), a reference-based metric that scores question-conditioned statements using bidirectional NLI. Under a monotonicity protocol testing whether metrics respect the taxonomy’s intended ordering, CAP outperforms established baselines.</abstract>
    <identifier type="citekey">yotkova-etal-2026-correct</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.1858</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1858/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>39666</start>
            <end>39685</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation
%A Yotkova, Elitsa
%A Kastreva, Violeta
%A Velkov, Petar
%A Boyanov, Hristo
%A Dimitrov, Dimitar Iliyanov
%A Nakov, Preslav
%A Koychev, Ivan
%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 yotkova-etal-2026-correct
%X Reliable evaluation of open-ended question answering remains a bottleneck for measuring answer correctness of modern LLMs. Unlike multiple-choice tasks, free-form answers may be correct in many surface forms and may fail in qualitatively different ways, including incompleteness, contradiction, overgeneration, and endorsement of false premises. Existing judgment-based and similarity-based metrics often collapse these distinctions. We address this gap with three reusable contributions. First, we introduce a semantic correctness taxonomy that assigns open-ended answers to eight ordered classes, separating verbose-but-correct answers from those contaminated by hallucinated content. Second, we release CAP-Correctness, an 8.8k-example benchmark spanning widely used QA datasets, and CAP-Statements, an 11k-example dataset for converting question-answer pairs into declarative statements for natural language inference (NLI) training and statement-based evaluation. Third, we introduce CAP (Context-Aware Precision), a reference-based metric that scores question-conditioned statements using bidirectional NLI. Under a monotonicity protocol testing whether metrics respect the taxonomy’s intended ordering, CAP outperforms established baselines.
%R 10.18653/2026.findings-emnlp.1858
%U https://aclanthology.org/2026.findings-emnlp.1858/
%U https://doi.org/10.18653/2026.findings-emnlp.1858
%P 39666-39685

Markdown (Informal)

[How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation](https://aclanthology.org/2026.findings-emnlp.1858/) (Yotkova et al., Findings 2026)

• How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation (Yotkova et al., Findings 2026)

ACL

• Elitsa Yotkova, Violeta Kastreva, Petar Velkov, Hristo Boyanov, Dimitar Iliyanov Dimitrov, Preslav Nakov, and Ivan Koychev. 2026. How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 39666–39685, Budapest, Hungary. Association for Computational Linguistics.