数学推理中的进化预提示优化
Evolutionary Pre-Prompt Optimization for Mathematical Reasoning
AI总结：
本文提出进化预提示优化方法，通过优化示例选择提升CoT预提示效果，在数学推理任务中取得显著提升。
摘要：
最近的进展表明，大型语言模型（LLMs）在获得少量任务特定示例的情况下表现出色，这种能力可以扩展到复杂的推理任务。特别是，少量学习与链式思维（CoT）方法的结合在引导模型朝着更逻辑一致的结论发展方面起到了关键作用[Wei等，2022b]。本文探讨了优化示例选择以设计有效CoT预提示的方法，并表明优化算法的选择，通常倾向于基于比较的方法如进化计算，显著提高了效率和可行性。具体来说，得益于有限的 exploitative 和 overfitted 优化，进化预提示优化（EPPO）在设计有效CoT预提示方面优于朴素的少量学习方法，在GSM8k和MathQA等基准数据集上的精确匹配分数超过10个绝对点。这些收益在各种情境下保持一致，并且在与自一致性（SC）结合时进一步增强。
英文摘要：
Recent advancements have highlighted that large language models (LLMs), when given a small set of task-specific examples, demonstrate remarkable proficiency, a capability that extends to complex reasoning tasks. In particular, the combination of few-shot learning with the chain-of-thought (CoT) approach has been pivotal in steering models towards more logically consistent conclusions [Wei et al. 2022b]. This paper explores the optimization of example selection for designing effective CoT pre-prompts and shows that the choice of the optimization algorithm, typically in favor of comparison-based methods such as evolutionary computation, significantly enhances efficacy and feasibility. Specifically, thanks to a limited exploitative and overfitted optimization, Evolutionary Pre-Prompt Optimization (EPPO) brings an improvement over the naive few-shot approach, exceeding 10 absolute points in exact match scores on benchmark datasets such as GSM8k and MathQA. These gains are consistent across various contexts and are further amplified when integrated with self-consistency (SC).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
