@inproceedings{wen-etal-2026-alignment,
    title = "Alignment or Formatting? Dissecting What On-Policy {DPO} Actually Learns",
    author = "Wen, Keyu  and
      Song, Yang  and
      Yang, Lijun  and
      Lin, Rui",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.2566/",
    pages = "58301--58309",
    ISBN = "979-8-89176-459-0"
}