@inproceedings{kulkarni-etal-2024-synthdst,
    title = "{S}ynth{DST}: Synthetic Data is All You Need for Few-Shot Dialog State Tracking",
    author = "Kulkarni, Atharva  and
      Tseng, Bo-Hsiang  and
      Moniz, Joel Ruben Antony  and
      Piraviperumal, Dhivya  and
      Yu, Hong  and
      Bhargava, Shruti",
    editor = "Graham, Yvette  and
      Purver, Matthew",
    booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2024",
    address = "St. Julian{'}s, Malta",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2024.eacl-long.120/",
    pages = "1988--2001",
    abstract = "In-context learning with Large Language Models (LLMs) has emerged as a promising avenue of research in Dialog State Tracking (DST). However, the best-performing in-context learning methods involve retrieving and adding similar examples to the prompt, requiring access to labeled training data. Procuring such training data for a wide range of domains and applications is time-consuming, expensive, and, at times, infeasible. While zero-shot learning requires no training data, it significantly lags behind the few-shot setup. Thus, {\textquoteleft}\textit{Can we efficiently generate synthetic data for any dialogue schema to enable few-shot prompting?}' Addressing this question, we propose , a data generation framework tailored for DST, utilizing LLMs. Our approach only requires the dialogue schema and a few hand-crafted dialogue templates to synthesize natural, coherent, and free-flowing dialogues with DST annotations. Few-shot learning using data from results in $4-5\%$ improvement in Joint Goal Accuracy over the zero-shot baseline on MultiWOZ 2.1 and 2.4. Remarkably, our few-shot learning approach recovers nearly 98{\%} of the performance compared to the few-shot setup using human-annotated training data."
}