Leveraging large language models to translate into easy language: An exploratory study on university websites

Diplôme Master Leveraging large language models to translate into easy language: An exploratory study on university websites eng 2025 author Luque Lopez Lucia 938116 director Morado Vazquez Lucia 0000-0002-0834-0734 792640 Département de traitement informatique multilingue (TINFM) Access to information is essential for everyone to actively participate in society. Easy language, as the most comprehensible language variety, is a key instrument in making content accessible to a larger audience. Recently, since the boom of large language models, their potential as a tool to improve the accessibility of written content has been tested in various contexts. This study aims to explore the intersection between easy language and large language models by determining, primarily, whether these models produce the best results when translating interlingually or intralingually. To do so, it featured an expert evaluation (which assessed the models’ output following easy language guidelines and translation quality metrics), an end-user evaluation (including a questionnaire and a usability study), as well as some tests with automatic metrics. By answering our main research question, we concluded that interlingual translation performed the best, a statement that is supported by our different evaluation processes. Easy language Accessibility Large language models Artificial intelligence Web accessibility Accessible communication Usability Dewey 410.2 Maîtrise universitaire en traduction et technologies : mention Localisation et traduction automatique 112 Département de traitement informatique multilingue 92 false e80ac639-3cb6-47af-bc5d-dcdd35869a43 Master thesis Public LuciaLuqueLopez_tesina_final.pdf 7550562 application/pdf 881252288c380ef2ea8785e94e7029ebb15832a580bd66fdfbc521449edf18a4 openAccess Faculté de traduction et d'interprétation / Département de traitement informatique multilingue

Title	Published in	Access level	OA Policy	Year	Views	Downloads

Leveraging large language models to translate into easy language: An exploratory study on university websites				2025	32	21

Archive ouverte UNIGE

Luque Lopez, Lucia

account_balance Affiliation entities

Affiliation entities