@inproceedings{chen-etal-2024-induct,
    title = "Induct-Learn: Short Phrase Prompting with Instruction Induction",
    author = "Chen, Po-Chun  and
      Wei, Sheng-Lun  and
      Huang, Hen-Hsen  and
      Chen, Hsin-Hsi",
    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/jlcl-multiple-ingestion/2024.emnlp-main.297/",
    doi = "10.18653/v1/2024.emnlp-main.297",
    pages = "5204--5231",
    abstract = "Large Language Models (LLMs) have demonstrated capability in {\textquotedblleft}instruction induction,{\textquotedblright} generating instructions from demonstrations (input-output pairs). However, existing methods often rely on large datasets or numerous examples, which is impractical and costly in real-world scenarios. In this work, we propose a low-cost, task-level framework called Induct-Learn. It induces pseudo instructions from a few demonstrations and a short phrase, adding a CoT process into existing demonstrations. When encountering new problems, the learned pseudo instructions and demonstrations with the pseudo CoT process can be combined into a prompt to guide the LLM`s problem-solving process. We validate our approach on the BBH-Induct and Evals-Induct datasets, and the results show that the Induct-Learn framework outperforms state-of-the-art methods. We also exhibit cross-model adaptability and achieve superior performance at a lower cost compared to existing methods."
}