思维多样性提升大语言模型的推理能力
Diversity of Thought Improves Reasoning Abilities of LLMs
AI总结：
本文提出通过自动生成多样化输入提示并集成多种推理路径的方法DIVSE和IDIV-SE，以提升大语言模型的复杂推理能力，并在规划与图着色基准上取得最先进性能。
摘要：
大语言模型（LLMs）在需要复杂推理的场景中表现不佳已有文献记载。尽管如此，通过指示模型将问题分解为更小的推理步骤，或通过修改解码步骤来集成多种生成结果，可以提升性能。然而，这些方法假设输入提示是固定的，并期望解码策略引入集成所需的多样性。本文讨论了如何创建并利用输入提示的变体作为思维多样性的一种手段。我们提出了一种方法，通过向LLM征求反馈来构思适合该问题的方法，从而自动提升提示多样性。随后，我们在多个推理调用中集成这些多样化提示，形成我们的方法DIVSE（DIVerse reasoning path Self-Ensemble，多样化推理路径自集成），或在单次推理调用中使用多样化方法；我们将后者称为IDIV-SE（In-call DIVerse reasoning path Self-Ensemble，调用内多样化推理路径自集成）。除了我们的方法优于先前工作外，DIV-SE（尤其是）在具有挑战性的规划和图着色基准上推进了最先进性能。我们的结果改善了准确率-成本权衡的帕累托前沿。
英文摘要：
Large language models (LLMs) are documented to struggle in settings that require complex reasoning. Nevertheless, instructing the model to break down the problem into smaller reasoning steps, or ensembling various generations through modifying decoding steps boosts performance. However, these methods assume that the input prompt is fixed and expect the decoding strategies to introduce the diversity needed for ensembling. In this work, we discuss how one can create and leverage variations of the input prompt as a means of diversity of thought. We propose a method that automatically improves prompt diversity by soliciting feedback from the LLM to ideate approaches that are apt for the problem. We then ensemble the diverse prompts in our method DIVSE (DIVerse reasoning path Self-Ensemble) across multiple inference calls, or use diverse approaches within a single inference call; we call the latter IDIV-SE (In-call DIVerse reasoning path Self-Ensemble). Apart from our approaches outperforming prior work, DIV-SE(in particular) advances state-of-the-art performance on the challenging planning and graph coloring benchmarks. Our results improve the Pareto frontier of the accuracy-cost trade-off.
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。
