Year: 2025
Type: conference-paper
Abstract: We revisit the BARTABSA framework for aspect-based sentiment analysis with modern decoder LLMs to assess the importance of explicit structure modeling today.Our updated implementation-BARTABSA++ 1 -features architectural enhancements that boost performance and training stability.Systematic testing with various encoder-decoder architectures shows that BARTABSA++ with BART-LARGE achieves state-of-the-art results, even surpassing a finetuned GPT-4O model.Our analysis indicates the encoder's representational quality is vital, while the decoder's role is minimal, explaining the limited benefits of scaling decoderonly LLMs for this task.These findings underscore the complementary roles of explicit structured modeling and large language models, indicating structured approaches remain competitive for tasks requiring precise relational information extraction.
Authors: Jan Pfister, Tom Völker, Anton Vlasjuk, Andreas Hotho
Institution: University of Würzburg
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4412944047