@inproceedings{wang-etal-2026-incomplete,
    title = "Incomplete In-context Learning",
    author = "Wang, Wenqiang  and
      Yujia, Wen  and
      Xiao, Yan  and
      Chen, Zhifeng  and
      Zhang, Yangshijie  and
      Chen, Peng  and
      Yang, Mingbo  and
      Cao, Xiaochun",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1931/",
    pages = "41629--41650",
    ISBN = "979-8-89176-390-6",
    abstract = "Existing \textit{In-context Learning (ICL)} typically assumes the retrieval dataset contains demonstrations for all output label spaces. However, in real-world scenarios, delays in dataset updates or incomplete data annotation may result in the retrieval dataset containing labeled demonstrations for only a subset of the output space. We refer to this phenomenon as an \textit{incomplete retrieval dataset} and define the in-context learning under this condition as \textit{Incomplete In-context Learning (IICL)}. To address IICL, we propose \textit{Iterative Judgments and Integrated Prediction (IJIP)}, a framework with train-free and train-based variants. For classification, the iterative judgments stage of IJIP reformulates an (m)-class problem into (m) binary tasks, converting IICL into standard ICL. The integrated prediction stage of IJIP then refines results using both the input and initial predictions. We further extend IJIP to text regression and generation, and introduce lightweight variants that reduce computation and token costs. Across six LLMs, seven tasks, and eight datasets, IJIP achieves state-of-the-art results under two incompleteness settings and even outperforms standard ICL with complete labels. IJIP also supports a semi-supervised variant and can serve as a plug-and-play enhancement for existing ICL and zero-shot methods."
}