@inproceedings{yun-etal-2025-ultrabench,
    title = "{ULTRABENCH}: Benchmarking {LLM}s under Extreme Fine-grained Text Generation",
    author = "Yun, Longfei  and
      Peng, Letian  and
      Shang, Jingbo",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-luhme/2025.findings-emnlp.835/",
    doi = "10.18653/v1/2025.findings-emnlp.835",
    pages = "15438--15453",
    ISBN = "979-8-89176-335-7",
    abstract = "Fine-grained control is essential for precise and customizable text generation, yet existing benchmarks evaluate models on only a few attributes, typically fewer than five. We introduce UltraBench, a new benchmark for extremely fine-grained controllable generation (EFCG), which evaluates large language models (LLMs) under dense, multi-attribute constraints. Each sample includes approximately 70 attributes, combining LLM-extracted soft constraints (e.g., style and tone) with programmatically enforced hard constraints (e.g., word count). Using UltraBench, we conduct a comprehensive evaluation of state-of-the-art LLMs and prompting strategies. Models such as GPT-4.1 and Qwen3-8B perform well on individual constraints, achieving instruction-level accuracy above 70{\%}, but consistently fail to satisfy all constraints simultaneously. To understand this limitation, we analyze model behavior across different dimensions. First, we observe a clear position bias: models tend to prioritize constraints presented later in the prompt while neglecting those that appear earlier. Second, we find that structural and formatting-related constraints are significantly more difficult to satisfy than content- or style-based ones, suggesting that current models struggle to coordinate global structure with token-level control. Finally, our error analysis reveals distinct failure modes: GPT-4.1 often attempts to follow constraints but falls short in precision, whereas LLaMA frequently omits constraints, particularly in multi-turn settings. These findings highlight fundamental limitations in EFCG and underscore the need for new methods that support dense, instruction-sensitive generation."
}