CardiffNLP at CLEARS-2025: Prompting Large Language Models for Plain Language and Easy-to-Read Text Rewriting
This work addresses text simplification for accessibility, but it is incremental as it applies standard prompting methods to a specific shared task.
The paper tackled Spanish text adaptation for plain language and easy-to-read rewriting using an LLM-prompting approach, achieving third place in Subtask 1 and second place in Subtask 2 of the CLEARS shared task.
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.