GRIPF at TSAR 2025 Shared Task Towards controlled CEFR level simplification with the help of inter-model interactions

David Alfter, Sebastian Gombert


Abstract
In this contribution to the CEFR level simplification TSAR 2025 Shared Task, we propose two systems, EZ-SCALAR and SAGA, that implement two differing approaches to prompting LLMs for proficiency-adapted simplification. Our results place us in the middle of the participating teams, and reveal that using external lexical resources to guide simplification improves overall results.
Anthology ID:
2025.tsar-1.10
Volume:
Proceedings of the Fourth Workshop on Text Simplification, Accessibility and Readability (TSAR 2025)
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Matthew Shardlow, Fernando Alva-Manchego, Kai North, Regina Stodden, Horacio Saggion, Nouran Khallaf, Akio Hayakawa
Venues:
TSAR | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
137–148
Language:
URL:
https://preview.aclanthology.org/ingest-emnlp/2025.tsar-1.10/
DOI:
Bibkey:
Cite (ACL):
David Alfter and Sebastian Gombert. 2025. GRIPF at TSAR 2025 Shared Task Towards controlled CEFR level simplification with the help of inter-model interactions. In Proceedings of the Fourth Workshop on Text Simplification, Accessibility and Readability (TSAR 2025), pages 137–148, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
GRIPF at TSAR 2025 Shared Task Towards controlled CEFR level simplification with the help of inter-model interactions (Alfter & Gombert, TSAR 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-emnlp/2025.tsar-1.10.pdf