用检索增强生成提升大模型解奥数物理题能力
Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving
- 让大模型通过检索历史物理题来辅助推理
- 在奥数级物理题上准确率显著提升
- 适合对高阶推理与知识检索感兴趣的学者
检索增强生成（RAG）结合基础模型已在多种任务中表现优异，但其在专家级推理——如奥林匹克级物理问题求解——中的潜力仍待探索。受学生备考时回顾过往题目的启发，我们研究了RAG在提升物理推理方面的可行性。为此，我们构建了PhoPile，一个专为奥林匹克级物理设计的高质量多模态数据集，包含图表、图像和方程，充分反映物理问题求解的多模态特性。基于PhoPile，我们系统评估了融合检索机制的大型语言模型（LLMs）与大型多模态模型（LMMs），涵盖多种检索器。结果表明，引入物理领域语料库的检索可有效提升模型表现，同时揭示了进一步研究检索增强型物理推理的关键挑战。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) with foundation models has achieved strong performance across diverse tasks, but their capacity for expert-level reasoning-such as solving Olympiad-level physics problems-remains largely unexplored. Inspired by the way students prepare for competitions by reviewing past problems, we investigate the potential of RAG to enhance physics reasoning in foundation models. We introduce PhoPile, a high-quality multimodal dataset specifically designed for Olympiad-level physics, enabling systematic study of retrieval-based reasoning. PhoPile includes diagrams, graphs, and equations, capturing the inherently multimodal nature of physics problem solving. Using PhoPile, we benchmark RAG-augmented foundation models, covering both large language models (LLMs) and large multimodal models (LMMs) with multiple retrievers. Our results demonstrate that integrating retrieval with physics corpora can improve model performance, while also highlighting challenges that motivate further research in retrieval-augmented physics reasoning.
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。