@inproceedings{bansal-etal-2025-comparing,
    title = "Comparing Bad Apples to Good Oranges Aligning Large Language Models via Joint Preference Optimization",
    author = "Bansal, Hritik  and
      Suvarna, Ashima  and
      Bhatt, Gantavya  and
      Peng, Nanyun  and
      Chang, Kai-Wei  and
      Grover, Aditya",
    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/mtsummit-25-ingestion/2025.findings-acl.39/",
    doi = "10.18653/v1/2025.findings-acl.39",
    pages = "701--723",
    ISBN = "979-8-89176-256-5",
    abstract = "A common technique for aligning large language models (LLMs) relies on acquiring human preferences by comparing multiple generations conditioned on a fixed context. This method, however, relies solely on pairwise comparisons, where the generations are evaluated within an identical context. While effective to such conditional preferences often fail to encompass the nuanced and multidimensional nature of human preferences. In this work, we revisit the traditional paradigm of preference acquisition and propose a new axis based on eliciting preferences jointly over the instruction-response pairs. Unlike prior preference optimizations, which are designed for conditional ranking protocols (e.g., DPO), we propose Joint Preference Optimization (JPO), a new preference optimization objective that upweights the joint probability of the chosen instruction-response pair over the rejected instruction-response pair. Interestingly, LLMs trained with joint instruction-response preference data using JPO outperform LLM trained with DPO by 5.2{\%} and 3.3{\%} win-rate for summarization and open-ended dialogue datasets, respectively. Our findings reveal that joint preferences over instruction and response pairs can significantly enhance the alignment of LLMs by tapping into a broader spectrum of human preference elicitation. The data and code is available athttps://github.com/Hritikbansal/jpo."
}