@inproceedings{parekh-etal-2025-dynamic,
    title = "Dynamic Strategy Planning for Efficient Question Answering with Large Language Models",
    author = "Parekh, Tanmay  and
      Prakash, Pradyot  and
      Radovic, Alexander  and
      Shekher, Akshay  and
      Savenkov, Denis",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.findings-naacl.336/",
    pages = "6038--6059",
    ISBN = "979-8-89176-195-7",
    abstract = "Research has shown an effectiveness of reasoning (e.g. Chain-of-Thought), planning (e.g. SelfAsk) and retrieval augmented generation strategies to improve performance of Large Language Models (LLMs) on various tasks, such as question answering. However, using a single fixed strategy for answering all different kinds of questions is sub-optimal in performance and inefficient in terms of generated tokens and retrievals. In our work, we propose a novel technique, DyPlan, to induce a dynamic strategy selection process in LLMs for cost-effective question-answering. DyPlan incorporates an initial decision step to select the most suitable strategy conditioned on the input question and guides the LLM{'}s response generation accordingly. We extend DyPlan to DyPlan-verify, adding an internal verification and correction process to further enrich the generated answer. Experimentation on three prominent multi-hop question answering (MHQA) datasets reveals how DyPlan can improve model performance by 7-13{\%} while reducing the cost by 11-32{\%} relative to the best baseline model."
}