Catalan Text Simplification with Large Language Models
Abstract
Automatic text simplification (ATS) is crucial for accessibility, yet it remains underexplored for low-resource languages. This thesis investigates sentence-level ATS for Catalan using large language models (LLMs). A performance analysis of three LLMs is conducted using the iDEM corpus as a benchmark and SARI as the ATS evaluation metric. Diverse prompt engineering techniques are employed to examine their impact on simplification quality. This work introduces a novel reward function that combines SARI with specific penalty terms to achieve better alignment. The reward function is designed for Group Relative Policy Optimization (GRPO) to guide LLMs toward a targeted simplification style. The effectiveness of GRPO with this reward function is demonstrated by post-training IberianLLM-7B-Instruct on the ASSET dataset. Following post-training, the model’s ATS performance improves, while also successfully suppressing negative behaviors. Cross-lingual transfer learning is explored by translating ASSET into Catalan and Spanish and post-training the model on them.
Keywords
Not available
Specialisations
Similar theses
- Learning to adapt: From structured domain adaptation to efficient in-context learning for large language models Zihao Xu · Rutgers University · 2026
- On the Safety Alignment of Large Language Models Mengxuan Hu · 2026
- Can Large Language Models become Innovation Experts? : Emulating Expert Evaluation of Innovation in Startups with Large Language Models Ricarda Nettinger · University of Turku · 2026
- Unstructured data for large language models Aleksandra Piktus · Sapienza University of Rome · 2026
- On the creative application of large language models Max Peeperkorn · University of Kent · 2026
- Cognitive Behaviours of Large Language Models Bryan Wilie · 2026
