@inproceedings{negi-etal-2026-large,
title = "Large Language Models as Automatic Annotators and Annotation Adjudicators for Fine-Grained Opinion Analysis",
author = "Negi, Gaurav and
Waskow, M.A. and
McCrae, John Philip and
Zayed, Omnia and
Buitelaar, Paul",
editor = {Aziz, Wilker and
Berant, Jonathan and
Eikema, Bryan and
Ilia, Evgenia and
de Marneffe, Marie-Catherine and
Plank, Barbara and
Shelmanov, Artem and
Swayamdipta, Swabha and
Tiedemann, J{\"o}rg and
Vazhentsev, Artem and
V{\'a}zquez, Ra{\'u}l and
Zerva, Chrysoula},
booktitle = "The Proceedings of the Third Workshop on Uncertainty-Aware {NLP}",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.uncertainlp-main.35/",
pages = "570--589",
ISBN = "979-8-89176-486-6",
abstract = "Fine-grained opinion analysis enables a detailed understanding of expressed sentiments and their corresponding targets. However, annotating domain-specific datasets requires substantial human effort and financial resources. To address this limitation, we investigate the feasibility of using large language models (LLMs) as automatic annotators for fine-grained opinion analysis. We use a declarative annotation pipeline to reduce prompt engineering when identifying fine-grained opinion spans, and compare rule-based voting against an LLM-based adjudicator for reconciling conflicting predictions. We trial the pipeline across different model sizes on the Aspect Sentiment Triplet Extraction (ASTE) and Aspect-Category-Opinion-Sentiment (ACOS) tasks. Our findings indicate a critical performance bifurcation: LLMs are reliable at the span level yet struggle to faithfully reproduce the relational structures connecting those spans. The better aggregation strategy depends on this complexity: voting suffices for triplets, while quadruples require an adjudicator that re-reads the source. Treating annotator disagreement as an informative signal rather than noise, we further show that agreement between LLM annotators is a calibrated predictor of correctness and can be used to delegate cases with high annotator disagreement to humans."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="negi-etal-2026-large">
<titleInfo>
<title>Large Language Models as Automatic Annotators and Annotation Adjudicators for Fine-Grained Opinion Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gaurav</namePart>
<namePart type="family">Negi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">M</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Waskow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">Philip</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omnia</namePart>
<namePart type="family">Zayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Buitelaar</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>The Proceedings of the Third Workshop on Uncertainty-Aware NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wilker</namePart>
<namePart type="family">Aziz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Berant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Eikema</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evgenia</namePart>
<namePart type="family">Ilia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Vazhentsev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chrysoula</namePart>
<namePart type="family">Zerva</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">979-8-89176-486-6</identifier>
</relatedItem>
<abstract>Fine-grained opinion analysis enables a detailed understanding of expressed sentiments and their corresponding targets. However, annotating domain-specific datasets requires substantial human effort and financial resources. To address this limitation, we investigate the feasibility of using large language models (LLMs) as automatic annotators for fine-grained opinion analysis. We use a declarative annotation pipeline to reduce prompt engineering when identifying fine-grained opinion spans, and compare rule-based voting against an LLM-based adjudicator for reconciling conflicting predictions. We trial the pipeline across different model sizes on the Aspect Sentiment Triplet Extraction (ASTE) and Aspect-Category-Opinion-Sentiment (ACOS) tasks. Our findings indicate a critical performance bifurcation: LLMs are reliable at the span level yet struggle to faithfully reproduce the relational structures connecting those spans. The better aggregation strategy depends on this complexity: voting suffices for triplets, while quadruples require an adjudicator that re-reads the source. Treating annotator disagreement as an informative signal rather than noise, we further show that agreement between LLM annotators is a calibrated predictor of correctness and can be used to delegate cases with high annotator disagreement to humans.</abstract>
<identifier type="citekey">negi-etal-2026-large</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.35/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>570</start>
<end>589</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large Language Models as Automatic Annotators and Annotation Adjudicators for Fine-Grained Opinion Analysis
%A Negi, Gaurav
%A Waskow, M. A.
%A McCrae, John Philip
%A Zayed, Omnia
%A Buitelaar, Paul
%Y Aziz, Wilker
%Y Berant, Jonathan
%Y Eikema, Bryan
%Y Ilia, Evgenia
%Y de Marneffe, Marie-Catherine
%Y Plank, Barbara
%Y Shelmanov, Artem
%Y Swayamdipta, Swabha
%Y Tiedemann, Jörg
%Y Vazhentsev, Artem
%Y Vázquez, Raúl
%Y Zerva, Chrysoula
%S The Proceedings of the Third Workshop on Uncertainty-Aware NLP
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-486-6
%F negi-etal-2026-large
%X Fine-grained opinion analysis enables a detailed understanding of expressed sentiments and their corresponding targets. However, annotating domain-specific datasets requires substantial human effort and financial resources. To address this limitation, we investigate the feasibility of using large language models (LLMs) as automatic annotators for fine-grained opinion analysis. We use a declarative annotation pipeline to reduce prompt engineering when identifying fine-grained opinion spans, and compare rule-based voting against an LLM-based adjudicator for reconciling conflicting predictions. We trial the pipeline across different model sizes on the Aspect Sentiment Triplet Extraction (ASTE) and Aspect-Category-Opinion-Sentiment (ACOS) tasks. Our findings indicate a critical performance bifurcation: LLMs are reliable at the span level yet struggle to faithfully reproduce the relational structures connecting those spans. The better aggregation strategy depends on this complexity: voting suffices for triplets, while quadruples require an adjudicator that re-reads the source. Treating annotator disagreement as an informative signal rather than noise, we further show that agreement between LLM annotators is a calibrated predictor of correctness and can be used to delegate cases with high annotator disagreement to humans.
%U https://aclanthology.org/2026.uncertainlp-main.35/
%P 570-589
Markdown (Informal)
[Large Language Models as Automatic Annotators and Annotation Adjudicators for Fine-Grained Opinion Analysis](https://aclanthology.org/2026.uncertainlp-main.35/) (Negi et al., UncertaiNLP 2026)
ACL