@inproceedings{saley-etal-2024-synergizing,
    title = "Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systems",
    author = "Saley, Vishal Vivek  and
      Das, Rocktim Jyoti  and
      Raghu, Dinesh  and
      Mausam",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/nameupper/2024.emnlp-main.320/",
    doi = "10.18653/v1/2024.emnlp-main.320",
    pages = "5596--5612",
    abstract = "End-to-end Task-Oriented Dialog (TOD) systems typically require extensive training datasets to perform well. In contrast, large language model (LLM) based TOD systems can excel even with limited data due to their ability to learn tasks through in-context exemplars. However, these models lack alignment with the style of responses in training data and often generate comprehensive responses, making it difficult for users to grasp the information quickly. In response, we propose SyncTOD that synergizes LLMs with task-specific hints to improve alignment in low-data settings. SyncTOD employs small auxiliary models to provide hints and select exemplars for in-context prompts. With ChatGPT, SyncTOD achieves superior performance compared to LLM-based baselines and SoTA models in low-data settings, while retaining competitive performance in full-data settings."
}