<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aryal-akomoize-2025-howard">
    <titleInfo>
        <title>Howard University - AI4PC at SemEval-2025 Task 3: Logit-based Supervised Token Classification for Multilingual Hallucination Span Identification Using XGBOD</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Saurav</namePart>
        <namePart type="family">Aryal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mildness</namePart>
        <namePart type="family">Akomoize</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sara</namePart>
            <namePart type="family">Rosenthal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aiala</namePart>
            <namePart type="family">Rosá</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Debanjan</namePart>
            <namePart type="family">Ghosh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marcos</namePart>
            <namePart type="family">Zampieri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-273-2</identifier>
    </relatedItem>
    <abstract>This paper describes our system for SemEval-2025 Task 3, Mu-SHROOM, which focuses on detecting hallucination spans in multilingual LLM outputs. We reframe hallucination detection as a point-wise anomaly detection problem by treating logits as time-series data. Our approach extracts features from token-level logits, addresses class imbalance with SMOTE, and trains an XGBOD model for probabilistic character-level predictions. Our system, which relies solely on information derived from the logits and token offsets (using pretrained tokenizers), achieves competitive intersection-over-union (IoU) and correlation scores on the validation and test set.</abstract>
    <identifier type="citekey">aryal-akomoize-2025-howard</identifier>
    <location>
        <url>https://aclanthology.org/2025.semeval-1.236/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>1790</start>
            <end>1794</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Howard University - AI4PC at SemEval-2025 Task 3: Logit-based Supervised Token Classification for Multilingual Hallucination Span Identification Using XGBOD
%A Aryal, Saurav
%A Akomoize, Mildness
%Y Rosenthal, Sara
%Y Rosá, Aiala
%Y Ghosh, Debanjan
%Y Zampieri, Marcos
%S Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-273-2
%F aryal-akomoize-2025-howard
%X This paper describes our system for SemEval-2025 Task 3, Mu-SHROOM, which focuses on detecting hallucination spans in multilingual LLM outputs. We reframe hallucination detection as a point-wise anomaly detection problem by treating logits as time-series data. Our approach extracts features from token-level logits, addresses class imbalance with SMOTE, and trains an XGBOD model for probabilistic character-level predictions. Our system, which relies solely on information derived from the logits and token offsets (using pretrained tokenizers), achieves competitive intersection-over-union (IoU) and correlation scores on the validation and test set.
%U https://aclanthology.org/2025.semeval-1.236/
%P 1790-1794

Markdown (Informal)

[Howard University - AI4PC at SemEval-2025 Task 3: Logit-based Supervised Token Classification for Multilingual Hallucination Span Identification Using XGBOD](https://aclanthology.org/2025.semeval-1.236/) (Aryal & Akomoize, SemEval 2025)

• Howard University - AI4PC at SemEval-2025 Task 3: Logit-based Supervised Token Classification for Multilingual Hallucination Span Identification Using XGBOD (Aryal & Akomoize, SemEval 2025)

ACL

• Saurav Aryal and Mildness Akomoize. 2025. Howard University - AI4PC at SemEval-2025 Task 3: Logit-based Supervised Token Classification for Multilingual Hallucination Span Identification Using XGBOD. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 1790–1794, Vienna, Austria. Association for Computational Linguistics.