aiqbench analysis
This research applies reinforcement learning via Group Relative Policy Optimization to enhance automatic text simplification in low-resource Catalan using Large Language Models. By introducing a novel reward function, the study successfully improves accessibility metrics and suppresses negative generation behaviors on specific benchmarks. The findings highlight the potential of RL fine-tuning to address linguistic gaps where cross-lingual transfer methods fall short.
Reinforcement Learning for improving Large Language Models' Catalan text simplification capabilities
arXiv:2609.04823v1 Announce Type: new Abstract: Although automatic text simplification (ATS) is critical for accessibility, its progress has not matched the rapid evolution of broader natural language processing techniques. This paper investigates the application of reinforcement learning (RL) to improve the quality of ATS for low-resource languages using Large Language Models (LLMs). The paper introduces a novel reward function, designed to guide LLMs toward a targeted simplification style with Group Relative Policy Optimization (GRPO), that combines the SARI metric with specific penalty components. The effectiveness of GRPO with this reward function is motivated and demonstrated by post-training IberianLLM-7B-Instruct on the ASSET dataset. After post-training on the English ASSET, the model's ATS performance improves on two curated Catalan benchmarks while also successfully suppressing previously observed negative behaviors. Cross-lingual transfer learning is explored by translating ASSET into Catalan and Spanish and post-training the model on each version, but these fail to show a significant improvement on the out-of-domain benchmark.
Abstract:Although automatic text simplification (ATS) is critical for accessibility, its progress has not matched the rapid evolution of broader natural language processing techniques. This paper investigates the application of reinforcement learning (RL) to improve the quality of ATS for low-resource languages using Large Language Models (LLMs). The paper introduces a novel reward function, designed to guide LLMs toward a targeted simplification style with Group Relative Policy Optimization (GRPO), that combines the SARI metric with specific penalty components. The effectiveness of GRPO with this reward function is motivated and demonstrated by post-training IberianLLM-7B-Instruct on the ASSET dataset. After post-training on the English ASSET, the model's ATS performance improves on two curated Catalan benchmarks while also successfully suppressing previously observed negative behaviors. Cross-lingual transfer learning is explored by translating ASSET into Catalan and Spanish and post-training the model on each version, but these fail to show a significant improvement on the out-of-domain benchmark.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2609.04823 [cs.CL]
(or arXiv:2609.04823v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.04823 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 249 words
Related coverage
Models Can't Remember Their Training. Neither Can You.
LessWrong · Jul 19, 2026
Latent reasoning architectures would likely undermine CoT, our strongest oversight tool
AI Alignment Forum · Sep 23, 2026
2026 BAIR Graduate Showcase
BAIR Blog · Jul 1, 2026
Opaque recurrence, and other AI terms that you should probably know
TechCrunch · Sep 7, 2026