# The Classics at SemEval-2026 Task 3: Combining Transformer Models and LLM-Generated Annotations for Dimensional Aspect-Based Sentiment Analysis

Source: [The Classics at SemEval-2026 Task 3: Combining Transformer Models and LLM-Generated Annotations for Dimensional Aspect-Based Sentiment Analysis](<https://www.sota2.com/research/paper/6a4c881485dba69fef8b27cb>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-08T05:00:13.057Z

Authors: Rafif Alshawi, Amit Raj, Aleksey Kudelya, Alexander Shirnin

Published: 2026-07-03T15:22:46.000Z

## Abstract

This paper presents an approach to the SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis. We investigate methods for moving beyond traditional categorical sentiment (e.g., positive or negative) to predict fine-grained, real-valued scores for sentiment "valence" (positivity) and "arousal" (intensity). We participate in two subtasks: predicting these scores for given aspects (Subtask 1) and extracting full sets of sentiment details, including aspects, categories, and opinions alongside their scores (Subtask 3). Our approach for the regression task involves a weighted ensemble of transformer-based encoder models. For the Russian language, we further enhance the input by using a large language model (LLM) to generate synthetic sentiment descriptions. For the extraction task, we fine-tune a decoder LLM to perform structured prediction, allowing the system to identify sentiment elements and estimate their numerical scores simultaneously.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Dimensional Aspect Sentiment Regression on Subtask 1 English Restaurant (test)](<https://www.sota2.com/research/sota/dimensional-aspect-sentiment-regression-on-subtask-1-english-restaurant-test.md>): Dimensional Aspect Sentiment Regression; Subtask 1 English Restaurant (test); RMSE: 1.23.

- [Dimensional Aspect Sentiment Regression on Subtask 1 English Laptop (test)](<https://www.sota2.com/research/sota/dimensional-aspect-sentiment-regression-on-subtask-1-english-laptop-test.md>): Dimensional Aspect Sentiment Regression; Subtask 1 English Laptop (test); RMSE: 1.33.

- [Dimensional Aspect Sentiment Regression on Subtask 1 Russian Restaurant (test)](<https://www.sota2.com/research/sota/dimensional-aspect-sentiment-regression-on-subtask-1-russian-restaurant-test.md>): Dimensional Aspect Sentiment Regression; Subtask 1 Russian Restaurant (test); RMSE: 1.64.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2607.03414>)

[PDF](<https://arxiv.org/pdf/2607.03414.pdf>)