@inproceedings{cattan-etal-2025-doubledipper,
    title = "{D}ouble{D}ipper: Recycling Contexts for Efficient and Attributed In-Context Learning",
    author = "Cattan, Arie  and
      Jacovi, Alon  and
      Fabrikant, Alex  and
      Herzig, Jonathan  and
      Aharoni, Roee  and
      Rashkin, Hannah  and
      Marcus, Dror  and
      Hassidim, Avinatan  and
      Matias, Yossi  and
      Szpektor, Idan  and
      Caciularu, Avi",
    editor = "Inui, Kentaro  and
      Sakti, Sakriani  and
      Wang, Haofen  and
      Wong, Derek F.  and
      Bhattacharyya, Pushpak  and
      Banerjee, Biplab  and
      Ekbal, Asif  and
      Chakraborty, Tanmoy  and
      Singh, Dhirendra Pratap",
    booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.findings-ijcnlp.42/",
    pages = "722--737",
    ISBN = "979-8-89176-303-6",
    abstract = "In this work, we propose DoubleDipper, a novel In-Context-Learning method that automatically generates few-shot examples for several QA tasks by {\_}recycling{\_} contexts. Specifically, given an input context (1-3k tokens) and a query, we generate additional query-output pairs from the given context as few-shot examples, while introducing the context only once. This ensures that the demonstrations are leveraging the same context as the target query while only adding a small number of tokens to the prompt. We further enhance each demonstration by instructing the model to {\_}explicitly{\_} identify the relevant paragraphs before the answer, which improves performance while providing fine-grained attribution to the answer source. We apply our method on multiple LLMs and obtain substantial improvements (+16 absolute points on average across models) on various QA datasets. Surprisingly, despite introducing only single-hop ICL examples, LLMs successfully generalize to multi-hop QA using our approach."
}