@inproceedings{pyun-etal-2025-improving,
    title = "Improving Dialogue State Tracking through Combinatorial Search for In-Context Examples",
    author = "Pyun, Haesung  and
      Park, Yoonah  and
      Jo, Yohan",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1393/",
    pages = "28694--28714",
    ISBN = "979-8-89176-251-0",
    abstract = "In dialogue state tracking (DST), in-context learning comprises a retriever that selects labeled dialogues as in-context examples and a DST model that uses these examples to infer the dialogue state of the query dialogue. Existing methods for constructing training data for retrievers suffer from three key limitations: (1) the synergistic effect of examples is not considered, (2) the linguistic characteristics of the query are not sufficiently factored in, and (3) scoring is not directly optimized for DST performance. Consequently, the retriever can fail to retrieve examples that would substantially improve DST performance. To address these issues, we present CombiSearch{---}a method that scores effective in-context examples based on their combinatorial impact on DST performance. Our evaluation on MultiWOZ shows that retrievers trained with CombiSearch surpass state-of-the-art models, achieving a 20{\texttimes} gain in data efficiency and generalizing well to the SGD dataset. Moreover, CombiSearch attains a 12{\%} absolute improvement in the upper bound DST performance over traditional approaches when no retrieval errors are assumed. This significantly increases the headroom for practical DST performance while demonstrating that existing methods rely on suboptimal data for retriever training."
}