@inproceedings{sia-duh-2023-context,
    title = "In-context Learning as Maintaining Coherency: A Study of On-the-fly Machine Translation Using Large Language Models",
    author = "Sia, Suzanna  and
      Duh, Kevin",
    editor = "Utiyama, Masao  and
      Wang, Rui",
    booktitle = "Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track",
    month = sep,
    year = "2023",
    address = "Macau SAR, China",
    publisher = "Asia-Pacific Association for Machine Translation",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.mtsummit-research.15/",
    pages = "173--185",
    abstract = "The phenomena of in-context learning has typically been thought of as ``learning from examples''. In this work which focuses on Machine Translation, we present a perspective of in-context learning as the desired generation task maintaining coherency with its context, i.e., the prompt examples. We first investigate randomly sampled prompts across 4 domains, and find that translation performance improves when shown in-domain prompts. Next, we investigate coherency for the in-domain setting, which uses prompt examples from a moving window. We study this with respect to other factors that have previously been identified in the literature such as length, surface similarity and sentence embedding similarity. Our results across 3 models (GPTNeo2.7B, Bloom3B, XGLM2.9B), and three translation directions (en$\rightarrow${\{}pt, de, fr{\}}) suggest that the long-term coherency of the prompts and the test sentence is a good indicator of downstream translation performance. In doing so, we demonstrate the efficacy of in-context Machine Translation for on-the-fly adaptation."
}