QuadAI at SemEval-2026 Task 3: Ensemble Learning of Hybrid RoBERTa and LLMs for Dimensional Aspect-Based Sentiment Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: de Vink, A. J. W., Ventirozos, Filippos Karolos, Amat-Lefort, Natalia, Han, Lifeng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915845333057536
author de Vink, A. J. W.
Ventirozos, Filippos Karolos
Amat-Lefort, Natalia
Han, Lifeng
author_facet de Vink, A. J. W.
Ventirozos, Filippos Karolos
Amat-Lefort, Natalia
Han, Lifeng
contents We present our system for SemEval-2026 Task 3 on dimensional aspect-based sentiment regression. Our approach combines a hybrid RoBERTa encoder, which jointly predicts sentiment using regression and discretized classification heads, with large language models (LLMs) via prediction-level ensemble learning. The hybrid encoder improves prediction stability by combining continuous and discretized sentiment representations. We further explore in-context learning with LLMs and ridge-regression stacking to combine encoder and LLM predictions. Experimental results on the development set show that ensemble learning significantly improves performance over individual models, achieving substantial reductions in RMSE and improvements in correlation scores. Our findings demonstrate the complementary strengths of encoder-based and LLM-based approaches for dimensional sentiment analysis. Our development code and resources will be shared at https://github.com/aaronlifenghan/ABSentiment
format Preprint
id arxiv_https___arxiv_org_abs_2603_07766
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle QuadAI at SemEval-2026 Task 3: Ensemble Learning of Hybrid RoBERTa and LLMs for Dimensional Aspect-Based Sentiment Analysis
de Vink, A. J. W.
Ventirozos, Filippos Karolos
Amat-Lefort, Natalia
Han, Lifeng
Computation and Language
Artificial Intelligence
We present our system for SemEval-2026 Task 3 on dimensional aspect-based sentiment regression. Our approach combines a hybrid RoBERTa encoder, which jointly predicts sentiment using regression and discretized classification heads, with large language models (LLMs) via prediction-level ensemble learning. The hybrid encoder improves prediction stability by combining continuous and discretized sentiment representations. We further explore in-context learning with LLMs and ridge-regression stacking to combine encoder and LLM predictions. Experimental results on the development set show that ensemble learning significantly improves performance over individual models, achieving substantial reductions in RMSE and improvements in correlation scores. Our findings demonstrate the complementary strengths of encoder-based and LLM-based approaches for dimensional sentiment analysis. Our development code and resources will be shared at https://github.com/aaronlifenghan/ABSentiment
title QuadAI at SemEval-2026 Task 3: Ensemble Learning of Hybrid RoBERTa and LLMs for Dimensional Aspect-Based Sentiment Analysis
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2603.07766