用知识增强框架提升大模型解物理题能力
Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models
- 构建公式库+检查清单，引导模型准确应用物理知识
- 在SciBench上平均准确率提升5.8%，达当前最优
- 适合需要严谨物理推理的AI教育与科学计算场景
物理问题涉及复杂推理与丰富物理知识，但现有大语言模型常因知识不足或误用而失效。为此，我们提出Physics Reasoner，一种知识增强框架，通过构建全面公式集提供显式物理知识，并利用包含详细指引的检查清单，引导有效知识应用。给定物理问题时，该框架分三阶段求解：问题分析、公式检索与引导推理。检查清单在分析与推理阶段促进模型自我优化。实验表明，Physics Reasoner有效缓解了知识缺失与错误应用问题，在SciBench上实现平均准确率5.8%的提升，达到当前最佳性能。
原文摘要 · Abstract (English)
Physics problems constitute a significant aspect of reasoning, necessitating complicated reasoning ability and abundant physics knowledge. However, existing large language models (LLMs) frequently fail due to a lack of knowledge or incorrect knowledge application. To mitigate these issues, we propose Physics Reasoner, a knowledge-augmented framework to solve physics problems with LLMs. Specifically, the proposed framework constructs a comprehensive formula set to provide explicit physics knowledge and utilizes checklists containing detailed instructions to guide effective knowledge application. Namely, given a physics problem, Physics Reasoner solves it through three stages: problem analysis, formula retrieval, and guided reasoning. During the process, checklists are employed to enhance LLMs' self-improvement in the analysis and reasoning stages. Empirically, Physics Reasoner mitigates the issues of insufficient knowledge and incorrect application, achieving state-of-the-art performance on SciBench with an average accuracy improvement of 5.8%.
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。