@inproceedings{prabhakar-etal-2026-policy,
    title = "On-Policy Distillation Meets Off-Policy {GRPO}: Training Compact Instruction-Following Rerankers",
    author = "Prabhakar, Vignesh  and
      Pan, Jialing  and
      Ankisettipalli, Anil Babu",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.477/",
    pages = "10001--10027",
    ISBN = "979-8-89176-462-0"
}