<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kalashnikova-etal-2026-turing">
    <titleInfo>
        <title>TURING: Evaluating Human Abilities to Identify AI-Generated Texts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Natalia</namePart>
        <namePart type="family">Kalashnikova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nicolas</namePart>
        <namePart type="family">De Bufala</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sophie</namePart>
        <namePart type="family">Fayad</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Laurent</namePart>
        <namePart type="family">Cervoni</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This study analyzes humans’ ability to identify AI-generated texts across 10 genres. We collected 9164 annotations from 214 participants on 500 texts (half human, half LLM-produced), and analyzed 7943 after quality screening. Our main findings are that the humans accuracy was above chance but far from perfect (around 59%), with a slight tendency to label texts as “Human-generated”. Their performance is influenced by the text genre (structural/factual formats easier to identify vs. complex genres) and by generating LLM. Annotators optionally selected three-level descriptors to justify decisions. While they had very limited effects on accuracy, their usage showed some association between text features (monotony, lack of cohesion or coherence) and “AI-generated” labeling. However, the linguistic features of the texts appear to have no robust impact after correction on human judgment. A small learning effect emerged but was practically negligible (0.1-0.2%), and personal characteristics of annotators had an impact on their accuracy, except age, which showed no effect. Finally, two automated detection tools were tested, reaching 88% accuracy on our distribution, clearly above humans, highlighting the value of human-tool combinations.</abstract>
    <identifier type="citekey">kalashnikova-etal-2026-turing</identifier>
    <identifier type="doi">10.63317/4e4ojwwryi8d</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.355/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>4527</start>
            <end>4535</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TURING: Evaluating Human Abilities to Identify AI-Generated Texts
%A Kalashnikova, Natalia
%A De Bufala, Nicolas
%A Fayad, Sophie
%A Cervoni, Laurent
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F kalashnikova-etal-2026-turing
%X This study analyzes humans’ ability to identify AI-generated texts across 10 genres. We collected 9164 annotations from 214 participants on 500 texts (half human, half LLM-produced), and analyzed 7943 after quality screening. Our main findings are that the humans accuracy was above chance but far from perfect (around 59%), with a slight tendency to label texts as “Human-generated”. Their performance is influenced by the text genre (structural/factual formats easier to identify vs. complex genres) and by generating LLM. Annotators optionally selected three-level descriptors to justify decisions. While they had very limited effects on accuracy, their usage showed some association between text features (monotony, lack of cohesion or coherence) and “AI-generated” labeling. However, the linguistic features of the texts appear to have no robust impact after correction on human judgment. A small learning effect emerged but was practically negligible (0.1-0.2%), and personal characteristics of annotators had an impact on their accuracy, except age, which showed no effect. Finally, two automated detection tools were tested, reaching 88% accuracy on our distribution, clearly above humans, highlighting the value of human-tool combinations.
%R 10.63317/4e4ojwwryi8d
%U https://aclanthology.org/2026.lrec-1.355/
%U https://doi.org/10.63317/4e4ojwwryi8d
%P 4527-4535

Markdown (Informal)

[TURING: Evaluating Human Abilities to Identify AI-Generated Texts](https://aclanthology.org/2026.lrec-1.355/) (Kalashnikova et al., LREC 2026)

• TURING: Evaluating Human Abilities to Identify AI-Generated Texts (Kalashnikova et al., LREC 2026)

ACL

• Natalia Kalashnikova, Nicolas De Bufala, Sophie Fayad, and Laurent Cervoni. 2026. TURING: Evaluating Human Abilities to Identify AI-Generated Texts. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 4527–4535, Palma de Mallorca, Spain. ELRA Language Resource Association.