<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="staliunaite-vlachos-2025-uncertain">
    <titleInfo>
        <title>Uncertain (Mis)Takes at LeWiDi-2025: Modeling Human Label Variation With Semantic Entropy</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ieva</namePart>
        <namePart type="given">Raminta</namePart>
        <namePart type="family">Staliūnaitė</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andreas</namePart>
        <namePart type="family">Vlachos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the The 4th Workshop on Perspectivist Approaches to NLP</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Gavin</namePart>
            <namePart type="family">Abercrombie</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Valerio</namePart>
            <namePart type="family">Basile</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simona</namePart>
            <namePart type="family">Frenda</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sara</namePart>
            <namePart type="family">Tonelli</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shiran</namePart>
            <namePart type="family">Dudy</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-350-0</identifier>
    </relatedItem>
    <abstract>The VariErrNLI task requires detecting the degree to which each Natural Language Inference (NLI) label is acceptable to a group of annotators. This paper presents an approach to VariErrNLI which incorporates measures of uncertainty, namely Semantic Entropy (SE), to model human label variation. Our method is based on the assumption that if two labels are plausible alternatives, then their explanations must be non-contradictory. We measure SE over Large Language Model (LLM)-generated explanations for a given NLI label, which represents the model uncertainty over the semantic space of possible explanations for that label. The system employs SE scores combined with an encoding of the inputs and generated explanations, and reaches a 0.31 Manhattan distance score on the test set, ranking joint first in the soft evaluation of VariErrNLI.</abstract>
    <identifier type="citekey">staliunaite-vlachos-2025-uncertain</identifier>
    <location>
        <url>https://aclanthology.org/2025.nlperspectives-1.23/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>256</start>
            <end>262</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Uncertain (Mis)Takes at LeWiDi-2025: Modeling Human Label Variation With Semantic Entropy
%A Staliūnaitė, Ieva Raminta
%A Vlachos, Andreas
%Y Abercrombie, Gavin
%Y Basile, Valerio
%Y Frenda, Simona
%Y Tonelli, Sara
%Y Dudy, Shiran
%S Proceedings of the The 4th Workshop on Perspectivist Approaches to NLP
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-350-0
%F staliunaite-vlachos-2025-uncertain
%X The VariErrNLI task requires detecting the degree to which each Natural Language Inference (NLI) label is acceptable to a group of annotators. This paper presents an approach to VariErrNLI which incorporates measures of uncertainty, namely Semantic Entropy (SE), to model human label variation. Our method is based on the assumption that if two labels are plausible alternatives, then their explanations must be non-contradictory. We measure SE over Large Language Model (LLM)-generated explanations for a given NLI label, which represents the model uncertainty over the semantic space of possible explanations for that label. The system employs SE scores combined with an encoding of the inputs and generated explanations, and reaches a 0.31 Manhattan distance score on the test set, ranking joint first in the soft evaluation of VariErrNLI.
%U https://aclanthology.org/2025.nlperspectives-1.23/
%P 256-262

Markdown (Informal)

[Uncertain (Mis)Takes at LeWiDi-2025: Modeling Human Label Variation With Semantic Entropy](https://aclanthology.org/2025.nlperspectives-1.23/) (Staliūnaitė & Vlachos, NLPerspectives 2025)

• Uncertain (Mis)Takes at LeWiDi-2025: Modeling Human Label Variation With Semantic Entropy (Staliūnaitė & Vlachos, NLPerspectives 2025)

ACL

• Ieva Raminta Staliūnaitė and Andreas Vlachos. 2025. Uncertain (Mis)Takes at LeWiDi-2025: Modeling Human Label Variation With Semantic Entropy. In Proceedings of the The 4th Workshop on Perspectivist Approaches to NLP, pages 256–262, Suzhou, China. Association for Computational Linguistics.