@article{robustposttrainingforgenerativerecommend,
  title = {Robust Post-Training for Generative Recommenders: Why Exponential Reward-Weighted SFT Outperforms RLHF},
  author = {Keertana Chidambaram and Sanath Kumar Krishnamurthy and Qiuling Xu and Ko-Jen Hsiao and Moumita Bhattacharya},
  year = {2026},
  eprint = {2603.10279},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.10279},
}