@inproceedings{lewoniewski-etal-2026-multi,
title = "Multi-Model Framework for Sentiment Annotation: A Use Case of Multilingual {W}ikipedia",
author = "Lewoniewski, W{\l}odzimierz and
Str{\'o}{\.z}yna, Milena and
Czuma{\l}owska, Izabela",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1830/",
doi = "10.18653/2026.findings-emnlp.1830",
pages = "39079--39090",
ISBN = "979-8-89176-462-0",
abstract = "In this work, we investigate whether data annotation can be automated using state-of-the-art large language models (LLMs), while maintaining high consistency and reliability. We propose a multi-model, multi-run framework in which several LLMs act as annotators and their outputs are aggregated using a strict consensus criterion to improve annotation robustness and reduce model-specific biases.\par The proposed approach is evaluated on a multilingual sentiment analysis task using lead sections of Wikipedia articles covering diverse topics in five languages. The resulting annotations are assessed using intra-model consistency, cross-model agreement, and standard inter-annotator agreement metrics. Additionally, we conducted human evaluation.\par The described framework enables scalable and reproducible data annotation, and the resulting dataset is publicly released to support further research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lewoniewski-etal-2026-multi">
<titleInfo>
<title>Multi-Model Framework for Sentiment Annotation: A Use Case of Multilingual Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Włodzimierz</namePart>
<namePart type="family">Lewoniewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milena</namePart>
<namePart type="family">Stróżyna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Izabela</namePart>
<namePart type="family">Czumałowska</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>In this work, we investigate whether data annotation can be automated using state-of-the-art large language models (LLMs), while maintaining high consistency and reliability. We propose a multi-model, multi-run framework in which several LLMs act as annotators and their outputs are aggregated using a strict consensus criterion to improve annotation robustness and reduce model-specific biases.\par The proposed approach is evaluated on a multilingual sentiment analysis task using lead sections of Wikipedia articles covering diverse topics in five languages. The resulting annotations are assessed using intra-model consistency, cross-model agreement, and standard inter-annotator agreement metrics. Additionally, we conducted human evaluation.\par The described framework enables scalable and reproducible data annotation, and the resulting dataset is publicly released to support further research.</abstract>
<identifier type="citekey">lewoniewski-etal-2026-multi</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1830</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1830/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>39079</start>
<end>39090</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Model Framework for Sentiment Annotation: A Use Case of Multilingual Wikipedia
%A Lewoniewski, Włodzimierz
%A Stróżyna, Milena
%A Czumałowska, Izabela
%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 lewoniewski-etal-2026-multi
%X In this work, we investigate whether data annotation can be automated using state-of-the-art large language models (LLMs), while maintaining high consistency and reliability. We propose a multi-model, multi-run framework in which several LLMs act as annotators and their outputs are aggregated using a strict consensus criterion to improve annotation robustness and reduce model-specific biases.\par The proposed approach is evaluated on a multilingual sentiment analysis task using lead sections of Wikipedia articles covering diverse topics in five languages. The resulting annotations are assessed using intra-model consistency, cross-model agreement, and standard inter-annotator agreement metrics. Additionally, we conducted human evaluation.\par The described framework enables scalable and reproducible data annotation, and the resulting dataset is publicly released to support further research.
%R 10.18653/2026.findings-emnlp.1830
%U https://aclanthology.org/2026.findings-emnlp.1830/
%U https://doi.org/10.18653/2026.findings-emnlp.1830
%P 39079-39090
Markdown (Informal)
[Multi-Model Framework for Sentiment Annotation: A Use Case of Multilingual Wikipedia](https://aclanthology.org/2026.findings-emnlp.1830/) (Lewoniewski et al., Findings 2026)
ACL