@inproceedings{nguyen-etal-2025-spec,
    title = "Spec-{TOD}: A Specialized Instruction-Tuned {LLM} Framework for Efficient Task-Oriented Dialogue Systems",
    author = "Nguyen, Vinh Quang  and
      Chieu, Nguyen Quang  and
      Pham, Hoang Viet  and
      Bui, Khac-Hoai Nam",
    editor = "B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Lef{\`e}vre, Fabrice  and
      Asher, Nicholas  and
      Kim, Seokhwan  and
      Merlin, Teva",
    booktitle = "Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
    month = aug,
    year = "2025",
    address = "Avignon, France",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-orcids-2024-emnlp/2025.sigdial-1.8/",
    pages = "133--145",
    abstract = "Task-oriented dialogue (TOD) systems facilitate goal-driven interactions between users and machines. While recent advances in deep learning have improved the performance, TOD systems often struggle in low-resource scenarios with limited labeled data. To address this challenge, we propose Spec-TOD, a novel framework designed to train an end-to-end TOD system with limited data. Spec-TOD introduces two main innovations: (i) a novel specialized end-to-end TOD framework that incorporates explicit task instructions for instruction-tuned large language models (LLMs), and (ii) an efficient training strategy that leverages lightweight, specialized LLMs to achieve strong performance with minimal supervision. Experiments on the MultiWOZ dataset, a widely used TOD benchmark, demonstrate that Spec-TOD achieves competitive results while significantly reducing the need for labeled data. These findings highlight the potential of the proposed framework in advancing efficient and effective TOD systems in low-resource settings."
}