用多样化提示并行激发大模型推理，提升小模型在复杂任务表现
Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasks
- 通过并行输入多样优化提示，让单个模型产生多条推理路径
- 3个1.5B模型的并行提示组合，在MATH上超越7B大模型
- 无需训练，适合资源有限但需高推理性能的场景
大型语言模型（LLMs），尤其是较小版本，在复杂推理任务中仍表现不佳。尽管推理时提示可引导推理过程，但现有方法多依赖顺序查询。集成方法提供了显著性能提升的可能，尤其得益于近期批量推理速度的提升。本文提出DIPPER，一种无需训练的新框架，能将单一LLM转化为高效的推理时集成模型。通过并行输入经过优化且多样化的提示，DIPPER激发模型产生多种推理路径，从而带来性能提升。我们在推理基准测试中实证表明显著改进：三个Qwen2-MATH-1.5B实例通过并行提示形成的集成，在MATH数据集上的表现优于一个更大的7B模型。
原文摘要 · Abstract (English)
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 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 7B model.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。