Do we still Need Human Annotators? Prompting Large Language Models for Aspect Sentiment Quad Prediction

URN to cite this document:: urn:nbn:de:bvb:355-epub-774474
DOI to cite this document:: 10.5283/epub.77447

Hellwig, Nils Constantin

; Fehle, Jakob

; Kruschwitz, Udo

; Wolff, Christian

License: Creative Commons Attribution 4.0
PDF - Published Version
arxiv
(3MB)

Date of publication of this fulltext: 29 Jul 2025 04:53

Alternative links to fulltext:Arxiv Publisher

Details

Preview: arxiv

Export bibliographical data

Abstract

Aspect sentiment quadruple prediction (ASQP) facilitates a detailed understanding of opinions expressed in a text by identifying the opinion term, aspect term, aspect category and sentiment polarity for each opinion. However, annotating a full set of training examples to finetune models for ASQP is a resource-intensive process. In this study, we explore the capabilities of large language models ...