@inproceedings{modi-szymanski-2026-rpi,
title = "{RPI} Team at {S}em{E}val-2026 Task 3: An {LLM}-Encoder Ensemble for Coarse-to-Fine Valence-Arousal Sentiment Prediction",
author = "Modi, Mohammed Shahid and
Szymanski, Boleslaw",
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-1.403/",
pages = "3218--3224",
ISBN = "979-8-89176-414-9",
abstract = "We present our coarse-to-fine Valence-Arousal (VA) ensemble system for subtask 1 of task 3 (DimABSA) which covers aspect-level VA prediction. We use a pair of trained Qwen 3 8B LoRA-tuned LLMs to predict coarse bins between 1 and 8, providing ordinal VA guidance signals along with distributional features. We then train an instruction-style, multilingual E5 encoder model with a multitask head using these LLM-derived guidance features to produce continuous VA predictions. At inference time, the same guidance signals are generated for the test set by the trained LLMs and fed into the trained encoder. This approach leverages the LLM as a high-level prior while relying on the encoder for precise calibration across languages and domains. Our system achieves an RMSEVA of 1.20 across six languages and five domains. We compare the joint VA model to separated valence and arousal models trained on coarsened ground truth data, showing that it outperforms them, particularly on arousal correlations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="modi-szymanski-2026-rpi">
<titleInfo>
<title>RPI Team at SemEval-2026 Task 3: An LLM-Encoder Ensemble for Coarse-to-Fine Valence-Arousal Sentiment Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Shahid</namePart>
<namePart type="family">Modi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boleslaw</namePart>
<namePart type="family">Szymanski</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>We present our coarse-to-fine Valence-Arousal (VA) ensemble system for subtask 1 of task 3 (DimABSA) which covers aspect-level VA prediction. We use a pair of trained Qwen 3 8B LoRA-tuned LLMs to predict coarse bins between 1 and 8, providing ordinal VA guidance signals along with distributional features. We then train an instruction-style, multilingual E5 encoder model with a multitask head using these LLM-derived guidance features to produce continuous VA predictions. At inference time, the same guidance signals are generated for the test set by the trained LLMs and fed into the trained encoder. This approach leverages the LLM as a high-level prior while relying on the encoder for precise calibration across languages and domains. Our system achieves an RMSEVA of 1.20 across six languages and five domains. We compare the joint VA model to separated valence and arousal models trained on coarsened ground truth data, showing that it outperforms them, particularly on arousal correlations.</abstract>
<identifier type="citekey">modi-szymanski-2026-rpi</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.403/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3218</start>
<end>3224</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RPI Team at SemEval-2026 Task 3: An LLM-Encoder Ensemble for Coarse-to-Fine Valence-Arousal Sentiment Prediction
%A Modi, Mohammed Shahid
%A Szymanski, Boleslaw
%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 modi-szymanski-2026-rpi
%X We present our coarse-to-fine Valence-Arousal (VA) ensemble system for subtask 1 of task 3 (DimABSA) which covers aspect-level VA prediction. We use a pair of trained Qwen 3 8B LoRA-tuned LLMs to predict coarse bins between 1 and 8, providing ordinal VA guidance signals along with distributional features. We then train an instruction-style, multilingual E5 encoder model with a multitask head using these LLM-derived guidance features to produce continuous VA predictions. At inference time, the same guidance signals are generated for the test set by the trained LLMs and fed into the trained encoder. This approach leverages the LLM as a high-level prior while relying on the encoder for precise calibration across languages and domains. Our system achieves an RMSEVA of 1.20 across six languages and five domains. We compare the joint VA model to separated valence and arousal models trained on coarsened ground truth data, showing that it outperforms them, particularly on arousal correlations.
%U https://aclanthology.org/2026.semeval-1.403/
%P 3218-3224
Markdown (Informal)
[RPI Team at SemEval-2026 Task 3: An LLM-Encoder Ensemble for Coarse-to-Fine Valence-Arousal Sentiment Prediction](https://aclanthology.org/2026.semeval-1.403/) (Modi & Szymanski, SemEval 2026)
ACL