@article{shapingexplanationssemanticrewardmodelin, title = {Shaping Explanations: Semantic Reward Modeling with Encoder-Only Transformers for GRPO}, author = {Francesco Pappone and Ruggero Marino Lazzaroni and Federico Califano and Niccolò Gentile and Roberto Marras}, year = {2025}, eprint = {2509.13081}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.13081}, }