@inproceedings{das-etal-2025-yinyang,
    title = "{Y}in{Y}ang-Align: A new Benchmark for Competing Objectives and Introducing Multi-Objective Preference based Text-to-Image Alignment",
    author = "Das, Amitava  and
      Narsupalli, Yaswanth  and
      Singh, Gurpreet  and
      Jain, Vinija  and
      Sharma, Vasu  and
      Trivedy, Suranjana  and
      Chadha, Aman  and
      Sheth, Amit",
    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/ingestion-acl-25/2025.findings-acl.1208/",
    pages = "23518--23598",
    ISBN = "979-8-89176-256-5",
    abstract = "Precise alignment in Text-to-Image (T2I) systems is crucial for generating visuals that reflect user intent while adhering to ethical and policy standards. Recent controversies, such as the Google Gemini-generated Pope image backlash, highlight the urgent need for robust alignment mechanisms. Building on alignment successes in Large Language Models (LLMs), this paper introduces YinYangAlign, a benchmarking framework designed to evaluate and optimize T2I systems across six inherently contradictory objectives. These objectives highlight core trade-offs, such as balancing faithfulness to prompts with artistic freedom and maintaining cultural sensitivity without compromising creativity. Alongside this benchmark, we propose the Contradictory Alignment Optimization (CAO) framework, an extension of Direct Preference Optimization (DPO), which employs multi-objective optimization techniques to address these competing goals. By leveraging per-axiom loss functions, synergy-driven global preferences, and innovative tools like the Synergy Jacobian, CAO achieves superior alignment across all objectives. Experimental results demonstrate significant improvements in fidelity, diversity, and ethical adherence, setting new benchmarks for the field. This work provides a scalable, effective approach to resolving alignment challenges in T2I systems while offering insights into broader AI alignment paradigms."
}