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.

翻译：科学知识日益分散在庞大且异质的科学文献中，其中重要的主张往往隐含、不断演变且存在内部争论。尽管大型语言模型（LLMs）在信息提取与摘要生成方面展现出卓越性能，但其恢复潜在科学共识的能力仍不明确。本文以凝聚态物理学中长期存在且争议激烈的高温超导（HTS）作为挑战性测试平台，对此问题展开研究。通过利用过去七十年间近18000篇高被引文献，我们构建了一个连接竞争性超导机制、材料家族、证据模态及引用关系的结构化知识图谱。研究发现，LLM提取的表征能够恢复连贯且具备物理可解释性的结构，包括材料家族依赖的机制图谱、证据特异性关联以及引用介导的科学认知时间演化。针对LLM的消融实验进一步表明，该全局结构在提示方式、解码策略及模型变体间均保持鲁棒性。我们的结果表明，LLM确实可作为可扩展的工具，用于解读以竞争性解释和知识演化为特征的学科领域的科学知识。