@inproceedings{hui-etal-2026-decif,
    title = "{D}ec{IF}: Improving Instruction-Following through Decomposition",
    author = "Hui, Tingfeng  and
      Zhu, Pengyu  and
      Ping, Bowen  and
      Tang, Ling  and
      Dong, Guanting  and
      Zhang, Yaqi  and
      Su, Sen",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.36/",
    pages = "848--867",
    ISBN = "979-8-89176-390-6",
    abstract = "We propose a novel data synthesis framework, DecIF, which automatically generates accurate and diverse instruction-following data from scratch for supervised fine-tuning (SFT) and reinforcement learning (RL), leveraging large language models (LLMs) and minimal external resources. By decomposing the data synthesis pipeline into fine-grained steps, DecIF achieves meticulous quality and diversity control over generated instruction-following data. Extensive experiments across both SFT and RL demonstrate DecIF{'}s strong capability to flexibly synthesize accurate instruction-following data for both paradigms compared to comprehensive baselines. Further analysis demonstrates the framework{'}s robustness, scalability, and computational efficiency in instruction-following data generation, while its modular design ensures straightforward implementation and reproducibility."
}