<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gralinski-etal-2025-oddballness">
    <titleInfo>
        <title>Oddballness: universal anomaly detection with language models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Filip</namePart>
        <namePart type="family">Gralinski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ryszard</namePart>
        <namePart type="family">Staruch</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Krzysztof</namePart>
        <namePart type="family">Jurkiewicz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-01</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 31st International Conference on Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Owen</namePart>
            <namePart type="family">Rambow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Leo</namePart>
            <namePart type="family">Wanner</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marianna</namePart>
            <namePart type="family">Apidianaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hend</namePart>
            <namePart type="family">Al-Khalifa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Barbara</namePart>
            <namePart type="given">Di</namePart>
            <namePart type="family">Eugenio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Schockaert</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, UAE</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present a new method to detect anomalies in texts (in general: in sequences of any data), using language models, in a totally unsupervised manner. The method considers probabilities (likelihoods) generated by a language model, but instead of focusing on low-likelihood tokens, it considers a new metric defined in this paper: oddballness. Oddballness measures how “strange” a given token is according to the language model. We demonstrate in grammatical error detection tasks (a specific case of text anomaly detection) that oddballness is better than just considering low-likelihood events, if a totally unsupervised setup is assumed.</abstract>
    <identifier type="citekey">gralinski-etal-2025-oddballness</identifier>
    <location>
        <url>https://aclanthology.org/2025.coling-main.183/</url>
    </location>
    <part>
        <date>2025-01</date>
        <extent unit="page">
            <start>2683</start>
            <end>2689</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Oddballness: universal anomaly detection with language models
%A Gralinski, Filip
%A Staruch, Ryszard
%A Jurkiewicz, Krzysztof
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F gralinski-etal-2025-oddballness
%X We present a new method to detect anomalies in texts (in general: in sequences of any data), using language models, in a totally unsupervised manner. The method considers probabilities (likelihoods) generated by a language model, but instead of focusing on low-likelihood tokens, it considers a new metric defined in this paper: oddballness. Oddballness measures how “strange” a given token is according to the language model. We demonstrate in grammatical error detection tasks (a specific case of text anomaly detection) that oddballness is better than just considering low-likelihood events, if a totally unsupervised setup is assumed.
%U https://aclanthology.org/2025.coling-main.183/
%P 2683-2689

Markdown (Informal)

[Oddballness: universal anomaly detection with language models](https://aclanthology.org/2025.coling-main.183/) (Gralinski et al., COLING 2025)

• Oddballness: universal anomaly detection with language models (Gralinski et al., COLING 2025)

ACL

• Filip Gralinski, Ryszard Staruch, and Krzysztof Jurkiewicz. 2025. Oddballness: universal anomaly detection with language models. In Proceedings of the 31st International Conference on Computational Linguistics, pages 2683–2689, Abu Dhabi, UAE. Association for Computational Linguistics.