@inproceedings{hu-etal-2025-dipper,
    title = "Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning Tasks",
    author = "Hu, Wenyang  and
      Lau, Gregory Kang Ruey  and
      Diwen, Liu  and
      Jizhuo, Chen  and
      Ng, See-Kiong  and
      Low, Bryan Kian Hsiang",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1801/",
    pages = "35546--35560",
    ISBN = "979-8-89176-332-6",
    abstract = "Large Language Models (LLMs), particularly smaller variants, still struggle with complex reasoning tasks. While inference-time prompting can guide reasoning, existing methods often rely on sequential queries. Ensemble approaches offer a promising path to performance gains, especially given recent batch inference speed-ups. This work introduces DIPPER, a novel, training-free framework that transforms a single LLM into an effective inference-time ensemble. By feeding the model an optimized and diverse set of prompts in parallel, DIPPER elicits varied reasoning paths, leading to performance gains. We empirically demonstrate significant improvements on mathematical reasoning benchmarks, such as MATH, where a DIPPER ensemble of three Qwen2-MATH-1.5B instances (via parallel prompting of a single model) outperforms a larger Qwen2-MATH-7B model."
}