大模型能从海量文献中提炼出高温超导领域的科学共识
Can LLMs extract scientific consensus? A case study in high-temperature superconductivity
- 构建包含近1.8万篇高被引论文的知识图谱，关联材料、机制与证据
- 大模型提取的结构与物理规律一致，展现不同材料家族的机制特征
- 适用于复杂争议领域，帮助研究人员快速把握知识演进脉络
科学知识日益分散于庞大且异质的文献中，重要主张常隐含、动态演变且存在内部争议。尽管大语言模型（LLMs）在信息抽取和摘要方面表现优异，但其挖掘潜在科学共识的能力尚不明确。本文以凝聚态物理中长期争论的高温超导（HTS）为挑战性测试场，基于过去七十年近18,000篇高被引论文，构建了一个结构化知识图谱，关联竞争性超导机制、材料体系、证据类型及引用关系。结果表明，LLM提取的表征能恢复出连贯且物理可解释的结构，包括材料族依赖的机制分布、证据特定的相关性，以及由引用驱动的科学信念演化过程。对LLM的消融实验显示，全局结构在提示方式、解码策略和模型差异下仍保持稳健。研究证实，大语言模型可作为解析具有多解释与动态演化的领域中科学知识的可扩展工具。
原文摘要 · Abstract (English)
Scientific knowledge is increasingly dispersed across vast and heterogeneous scientific literature, where important claims are often implicit, evolving, and internally debated. While large language models (LLMs) have shown impressive performance in information extraction and summarization, their ability to recover latent scientific consensus remains unclear. Here, we investigate this problem in the context of high-temperature superconductivity (HTS), a long-standing and highly debated topic in condensed matter physics, as a challenging testbed. Using near 18,000 highly-cited publications over the past seven decades, we construct a structured knowledge graph linking competing superconducting mechanisms, material families, evidential modalities, and citation relations. We find that LLM-extracted representations recover coherent and physically interpretable structures, including family-dependent mechanism profiles, evidence-specific correlations, and citation-mediated temporal evolution of scientific beliefs. Ablation studies on LLM further show that the global structure remains robust across prompting, decoding, and model variations. Our results suggest that LLMs can indeed serve as scalable tools for deciphering scientific knowledge in domains characterized by competing interpretations and evolving knowledge.
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。