@inproceedings{zhang-etal-2025-pfdial,
    title = "{PFD}ial: A Structured Dialogue Instruction Fine-tuning Method Based on {UML} Flowcharts",
    author = "Zhang, Ming  and
      Wang, Yuhui  and
      Shen, Yujiong  and
      Yang, Tingyi  and
      Jiang, Changhao  and
      Wu, Yilong  and
      Dou, Shihan  and
      Chen, Qinhao  and
      Xi, Zhiheng  and
      Zhang, Zhihao  and
      Dong, Yi  and
      Wang, Zhen  and
      Fei, Zhihui  and
      Wan, Mingyang  and
      Liang, Tao  and
      Ma, Guojun  and
      Zhang, Qi  and
      Gui, Tao  and
      Huang, Xuanjing",
    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.134/",
    pages = "2626--2649",
    ISBN = "979-8-89176-256-5",
    abstract = "Process-driven dialogue systems, which operate under strict predefined process constraints, are essential in customer service and equipment maintenance scenarios. Although Large Language Models (LLMs) have shown remarkable progress in dialogue and reasoning, they still struggle to solve these strictly constrained dialogue tasks. To address this challenge, we construct **P**rocess **F**low **Dial**ogue (**PFDial**) dataset, which contains 12,705 high-quality Chinese dialogue instructions derived from 440 flowcharts containing 5,055 process nodes. Based on PlantUML specification, each UML flowchart is converted into atomic dialogue units i.e., structured five-tuples. Experimental results demonstrate that a 7B model trained with merely 800 samples, and a 0.5B model trained on total data both can surpass 90{\%} accuracy. Additionally, the 8B model can surpass GPT-4o up to 43.88{\%} with an average of 11.00{\%}. We further evaluate models' performance on challenging backward transitions in process flows and conduct an in-depth analysis of various dataset formats to reveal their impact on model performance in handling decision and sequential branches. The data is released in https://github.com/KongLongGeFDU/PFDial."
}