具体化命题提示解决大语言模型中的组合-知识二分法
Concretized Proposition Prompting Resolves Composition-Knowledge Dichotomy in Large Language Models
AI总结：
研究针对大语言模型组合-知识二分法难题，提出具体化命题提示（CPP）框架。通过明确相关命题具体化，提升推理性能，尤其在医学基准测试中表现突出，且可扩展到多种模型和参数规模，弥合两类方法差距，解决了二分法问题。
摘要：
大语言模型（LLMs）在平衡组合性与知识丰富性方面常常面临困难，我们将此挑战定义为组合-知识二分法。为解决这一问题，我们提出了具体化命题提示（CPP）框架，该框架能明确地将与问题相关的命题具体化。实验结果表明，CPP显著提高了推理性能，尤其在对精确知识要求极高的医学基准测试中表现出色，在注重演绎推理的数学基准测试中也具有竞争力。此外，实验还表明CPP可扩展到各种基础模型和参数规模，是弥合基于组合和基于知识方法之间差距的基本范式。因此，CPP通过为逻辑组织和基于事实的推理提供坚实基础，解决了组合-知识二分法。
英文摘要：
LLMs often struggle to balance compositionality with knowledgeability, a challenge we define as Composition-Knowledge Dichotomy. To address this, we propose Concretized Proposition Prompting (CPP), a framework that explicitly concretizes propositions relevant to questions. The results demonstrate that CPP significantly enhances reasoning performance, particularly in medical benchmarks where precise knowledge is paramount, while being competitive on math benchmarks where deductive reasoning is prioritized. Additional experiments reveal that CPP is scalable to various foundation models and parameter sizes, being a fundamental paradigm that bridges the gap between composition- and knowledge-based approaches. Consequently, CPP resolves the composition-knowledge dichotomy by providing a solid foundation for logically organized and factually grounded reasoning.
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。
