@inproceedings{yamada-etal-2026-takoyaki,
title = "Takoyaki at {S}em{E}val-2026 Task 3: Ensembling {LLM} Predictions using Demonstration Retrieval for Dimensional Aspect-based Sentiment Analysis",
author = "Yamada, Kosuke and
Takase, Sho and
Kohita, Ryosuke",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.219/",
pages = "1707--1723",
ISBN = "979-8-89176-414-9",
abstract = "This paper describes our system for SemEval-2026 Task 3 (DimABSA). We participate in Subtask 2 (DimASTE), which requires extracting triplets of aspect term, opinion term, and valence-arousal scores from review sentences, and Subtask 3 (DimASQP), which additionally requires aspect category classification to form quadruplets. Our proposed system consists of a multi-step pipeline: (1) retrieval-based in-context learning using BM25 to select relevant demonstrations for LLM inference, (2) agreement-based ensemble combining LLM predictions from multiple retrieval variants, and, for a subset of datasets, (3) error-pattern correction refining uncertain predictions using correction rule sets based on training data. Retrieval-based ICL and the agreement-based ensemble show consistent improvements across languages and domains. Error-pattern correction yields further improvement for the Japanese dataset. To further investigate output quality beyond automated evaluation metrics, we conducted human evaluation. The results suggest that LLM-based labeling achieves higher agreement with gold labels than human annotators, and additionally indicate a discrepancy between automated scores and practical output quality."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yamada-etal-2026-takoyaki">
<titleInfo>
<title>Takoyaki at SemEval-2026 Task 3: Ensembling LLM Predictions using Demonstration Retrieval for Dimensional Aspect-based Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kosuke</namePart>
<namePart type="family">Yamada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sho</namePart>
<namePart type="family">Takase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryosuke</namePart>
<namePart type="family">Kohita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</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">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>This paper describes our system for SemEval-2026 Task 3 (DimABSA). We participate in Subtask 2 (DimASTE), which requires extracting triplets of aspect term, opinion term, and valence-arousal scores from review sentences, and Subtask 3 (DimASQP), which additionally requires aspect category classification to form quadruplets. Our proposed system consists of a multi-step pipeline: (1) retrieval-based in-context learning using BM25 to select relevant demonstrations for LLM inference, (2) agreement-based ensemble combining LLM predictions from multiple retrieval variants, and, for a subset of datasets, (3) error-pattern correction refining uncertain predictions using correction rule sets based on training data. Retrieval-based ICL and the agreement-based ensemble show consistent improvements across languages and domains. Error-pattern correction yields further improvement for the Japanese dataset. To further investigate output quality beyond automated evaluation metrics, we conducted human evaluation. The results suggest that LLM-based labeling achieves higher agreement with gold labels than human annotators, and additionally indicate a discrepancy between automated scores and practical output quality.</abstract>
<identifier type="citekey">yamada-etal-2026-takoyaki</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.219/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1707</start>
<end>1723</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Takoyaki at SemEval-2026 Task 3: Ensembling LLM Predictions using Demonstration Retrieval for Dimensional Aspect-based Sentiment Analysis
%A Yamada, Kosuke
%A Takase, Sho
%A Kohita, Ryosuke
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F yamada-etal-2026-takoyaki
%X This paper describes our system for SemEval-2026 Task 3 (DimABSA). We participate in Subtask 2 (DimASTE), which requires extracting triplets of aspect term, opinion term, and valence-arousal scores from review sentences, and Subtask 3 (DimASQP), which additionally requires aspect category classification to form quadruplets. Our proposed system consists of a multi-step pipeline: (1) retrieval-based in-context learning using BM25 to select relevant demonstrations for LLM inference, (2) agreement-based ensemble combining LLM predictions from multiple retrieval variants, and, for a subset of datasets, (3) error-pattern correction refining uncertain predictions using correction rule sets based on training data. Retrieval-based ICL and the agreement-based ensemble show consistent improvements across languages and domains. Error-pattern correction yields further improvement for the Japanese dataset. To further investigate output quality beyond automated evaluation metrics, we conducted human evaluation. The results suggest that LLM-based labeling achieves higher agreement with gold labels than human annotators, and additionally indicate a discrepancy between automated scores and practical output quality.
%U https://aclanthology.org/2026.semeval-1.219/
%P 1707-1723
Markdown (Informal)
[Takoyaki at SemEval-2026 Task 3: Ensembling LLM Predictions using Demonstration Retrieval for Dimensional Aspect-based Sentiment Analysis](https://aclanthology.org/2026.semeval-1.219/) (Yamada et al., SemEval 2026)
ACL