@inproceedings{sultania-etal-2025-routenator,
    title = "{R}oute{N}ator: A Router-Based Multi-Modal Architecture for Generating Synthetic Training Data for Function Calling {LLM}s",
    author = "Belavadi, Vibha  and
      Vatsa, Tushar  and
      Sultania, Dewang  and
      Suresha, Suhas  and
      Verma, Ishita  and
      Chen, Cheng  and
      King, Tracy Holloway  and
      Friedrich, Michael",
    editor = "Shi, Weijia  and
      Yu, Wenhao  and
      Asai, Akari  and
      Jiang, Meng  and
      Durrett, Greg  and
      Hajishirzi, Hannaneh  and
      Zettlemoyer, Luke",
    booktitle = "Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-degibert/2025.knowledgenlp-1.10/",
    doi = "10.18653/v1/2025.knowledgenlp-1.10",
    pages = "129--140",
    ISBN = "979-8-89176-229-9",
    abstract = "This paper addresses fine-tuning Large Language Models (LLMs) for function calling tasks when real user interaction data is unavailable. In digital content creation tools, where users express their needs through natural language queries that must be mapped to API calls, the lack of real-world task-specific data and privacy constraints for training on it necessitate synthetic data generation. Existing approaches to synthetic data generation fall short in diversity and complexity, failing to replicate real-world data distributions and leading to suboptimal performance after LLM fine-tuning. We present a novel router-based architecture that leverages domain resources like content metadata and structured knowledge graphs, along with text-to-text and vision-to-text language models to generate high-quality synthetic training data. Our architecture{'}s flexible routing mechanism enables synthetic data generation that matches observed real-world distributions, addressing a fundamental limitation of traditional approaches. Evaluation on a comprehensive set of real user queries demonstrates significant improvements in both function classification accuracy and API parameter selection. Models fine-tuned with our synthetic data consistently outperform traditional approaches, establishing new benchmarks for function calling tasks."
}