@inproceedings{galatolo-etal-2025-visualising,
    title = "Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language Models",
    author = "Galatolo, Alessio  and
      Dai, Zhenbang  and
      Winkle, Katie  and
      Beloucif, Meriem",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.findings-acl.897/",
    pages = "17446--17461",
    ISBN = "979-8-89176-256-5"
}