Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

CardiffNLP at CLEARS-2025: Prompting large language models for plain language and easy-to-read text rewriting

Ayesh, Mutaz, Gutiérrez Rolón, Nicolas and Alva Manchego, Fernando ORCID: https://orcid.org/0000-0001-6218-8377 2025. CardiffNLP at CLEARS-2025: Prompting large language models for plain language and easy-to-read text rewriting. Presented at: IberLEF 2025, Zaragoza, Spain, 23 September 2025. Published in: Jiménez-Zafra, Salud Maria, González-Barba, Jose Angel, Chiruzzo, Luis, Alcántara, Tania and Álvarez-Carmona, Miguel A. eds. Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2025). CEUR Workshop Proceedings. , vol.4098

[thumbnail of CLEARS_paper2.pdf] PDF - Published Version
Available under License Creative Commons Attribution.

Download (988kB)

Abstract

This paper details the CardiffNLP team’s contribution to the CLEARS shared task on Spanish text adaptation, hosted by IberLEF 2025. The shared task contained two subtasks and the team submitted to both. Our team took an LLM-prompting approach with different prompt variations. While we initially experimented with LLaMA-3.2, we adopted Gemma-3 for our final submission, and landed third place in Subtask 1 and second place in Subtask 2. We detail our numerous prompt variations, examples, and experimental results.

Item Type: Conference or Workshop Item - published (Paper)
Date Type: Published Online
Status: Published
Schools: Schools > Computer Science & Informatics
Additional Information: For full list of editors see https://ceur-ws.org/Vol-4098/
ISSN: 1613-0073
Related URLs:
Date of First Compliant Deposit: 1 June 2026
Last Modified: 04 Aug 2026 21:15
URI: https://orca.cardiff.ac.uk/id/eprint/187350

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics