@inproceedings{jung-etal-2025-binary,
    title = "Binary Classifier Optimization for Large Language Model Alignment",
    author = "Jung, Seungjae  and
      Han, Gunsoo  and
      Nam, Daniel Wontae  and
      On, Kyoung-Woon",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.93/",
    pages = "1858--1872",
    ISBN = "979-8-89176-251-0",
    abstract = "In real-world services such as ChatGPT, aligning models based on user feedback is crucial for improving model performance. However, due to the simplicity and convenience of providing feedback, users typically offer only basic binary signals, such as `thumbs-up' or `thumbs-down'. Most existing alignment research, on the other hand, relies on preference-based approaches that require both positive and negative responses as a pair. We propose Binary Classifier Optimization (BCO), a technique that effectively aligns LLMs using only binary feedback. BCO trains a binary classifier, where the logit serves as an implicit reward, effectively minimizing the Direct Preference Optimization (DPO) loss. We demonstrate that the binary cross-entropy loss employed in classifier training acts as an upper bound for the DPO loss. Additionally, a novel reward shift technique further minimizes the gap between the losses. We validate our methodology in two settings: first, on a paired preference dataset, where our method performs on par with DPO; and second, on a Likert-5 scale annotation dataset which stems from real users' queries. Our model consistently demonstrates effective and robust alignment across four base LLMs and three different datasets, showcasing the strength of our approach to learning from binary signals."
}