TypedThinker:通过类型化思维多样化大型语言模型推理
TypedThinker: Diversify Large Language Model Reasoning with Typed Thinking
AI总结:
TypedThinker通过预测合适的推理类型并提供示例,多样化LLM的推理方式,在逻辑和数学任务上分别提升Mistral 7B、LLaMA3 8B和Qwen 2 7B的性能3.4%、6.5%和7%,无需知识蒸馏。
摘要:
大型语言模型(LLMs)在解决复杂问题方面展现了强大的推理能力。然而,当前的方法主要通过细化思维来增强推理,却忽视了推理类型的多样性。LLMs通常采用演绎推理,从给定条件逐步推进,这限制了它们在问题解决过程中的探索。我们的分析表明,某些问题只能通过特定的推理策略(如归纳、溯因或类比推理)来解决。然而,整合多样化的推理方法面临两个关键挑战:为每个问题识别合适的推理类型,以及在问题解决过程中利用这种方法。因此,我们提出了TypedThinker,它基于问题及其先前的有效性来预测合适的推理类型,并提供相关示例以引导LLMs应用这些策略。实验结果显示,在多个基准测试中取得了显著改进,在逻辑和数学推理任务上,Mistral 7B的性能提升了3.4%,LLaMA3 8B提升了6.5%,Qwen 2 7B提升了7%。TypedThinker无需从更大模型中进行知识蒸馏即可增强LLM推理能力。它可以集成到更先进的系统(如GPT-4o)或专门模型(如MetaMath)中,以多样化它们的推理方法并提升其问题解决能力。
英文摘要:
Large Language Models (LLMs) have demonstrated strong reasoning capabilities in solving complex problems. However, current approaches primarily enhance reasoning through the elaboration of thoughts while neglecting the diversity of reasoning types. LLMs typically employ deductive reasoning, proceeding step-by-step from given conditions, which limits their exploration during problem-solving. Our analysis reveals that certain problems are exclusively solvable through specific reasoning strategies like inductive, abductive, or analogical reasoning. However, incorporating diverse reasoning approaches presents two key challenges: identifying the appropriate reasoning type for each problem and exploiting this approach during problem-solving. Therefore, we propose the TypedThinker that predicts suitable reasoning types based on the problem and their previous effectiveness and provides relevant demonstrations to guide LLMs in applying these strategies. Experimental results show significant improvements across multiple benchmarks, with performance gains of 3.4% for Mistral 7B, 6.5% for LLaMA3 8B, and 7% for Qwen 2 7B on logical and mathematical reasoning tasks. TypedThinker enhances LLM reasoning without requiring knowledge distillation from larger models. It can be integrated into more advanced systems like GPT-4o or specialized models like MetaMath to diversify their reasoning approaches and improve their problem-solving capabilities.
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。