Advancing Cross-lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models
Abstract
Aspect-based sentiment analysis (ABSA) has made significant strides, yet challenges remain for low-resource languages due to the predominant focus on English. Current cross-lingual ABSA studies often centre on simpler tasks and rely heavily on external translation tools. In this paper, we present a novel sequence-to-sequence method for compound ABSA tasks that eliminates the need for such tools. Our approach, which uses constrained decoding, improves cross-lingual ABSA performance by up to 10\%. This method broadens the scope of cross-lingual ABSA, enabling it to handle more complex tasks and providing a practical, efficient alternative to translation-dependent techniques. Furthermore, we compare our approach with large language models (LLMs) and show that while fine-tuned multilingual LLMs can achieve comparable results, English-centric LLMs struggle with these tasks.
Cite
@article{arxiv.2508.10366,
title = {Advancing Cross-lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models},
author = {Jakub Šmíd and Pavel Přibáň and Pavel Král},
journal= {arXiv preprint arXiv:2508.10366},
year = {2025}
}
Comments
Published in Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2 (ICAART 2025). Official version: https://www.scitepress.org/Link.aspx?doi=10.5220/0013349400003890