@article{adaptingreinforcementlearningwithchainof,
  title = {Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes},
  author = {Mohamed Bayan Kmainasi and Mucahid Kutlu and Ali Ezzat Shahroor and Abul Hasnat and Firoj Alam},
  year = {2026},
  eprint = {2606.15307},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.15307},
}