Repeated post-training is not Self-improving: Diagnosing Scientific Amnesia in Continual DPO Pipelines
- 2026-06-17
- 0
@misc{lin2026repeated,
title = {Repeated post-training is not Self-improving: Diagnosing Scientific Amnesia in Continual DPO Pipelines},
author = {Jianzhe Lin and Fang Wang and Xiaolin Li and Rajeshkumar Golani and Jubin Chheda},
year = {2026},
eprint = {2606.21089},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.21089},
}