@article{anempiricalstudyofrewardspecificationand, title = {An Empirical Study of Reward Specification and Benchmark Reliability in GRPO-based LLM Unlearning}, author = {Rubén Balbastre and Juan Manuel Orduña and Mariano Pérez}, year = {2026}, eprint = {2608.17804}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.17804}, }