@article{adversarialdpoharnessingharmfuldatafor,
  title = {Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents},
  author = {San Kim and Gary Geunbae Lee},
  year = {2024},
  eprint = {2405.12900},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.12900v1},
}