arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2606.07570cs.DLcs.LG
收藏

LLMs能否提取科学共识?以高温超导为例

Can LLMs extract scientific consensus? A case study in high-temperature superconductivity

Center for Computational Science and Engineering, MIT(MIT计算科学与工程中心);Department of Materials Science and Engineering, MIT(MIT材料科学与工程系);Department of Physics, MIT(MIT物理系);Department of Nuclear Science and Engineering, MIT(MIT核科学与工程系);John A. Paulson School of Engineering and Applied Sciences, Harvard University(哈佛大学约翰·A·保罗森工程与应用科学学院);Department of Chemistry, Emory University(埃默里大学化学系);Department of Physics, University of Connecticut(康涅狄格大学物理系);Department of Physics and Texas Center for Superconductivity, University of Houston(休斯顿大学物理系和德克萨斯超导中心)

Mouyang Cheng, Wenhao He, Zhuotao Jin, Bowen Yu, Ju Li, Boris Kozinsky, Yao Wang, Pavel Volkov, Liangzi Deng, Ching-Wu Chu, Xiao-Gang Wen, Mingda Li

AI总结:

本研究以高温超导领域为测试平台,利用近18,000篇高被引文献构建知识图谱,发现LLM提取的表征能恢复出连贯且物理可解释的结构,表明LLM可作为解码竞争性科学知识的可扩展工具。

摘要:

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是隐含的、不断演变的,并且存在内部争议。尽管大型语言模型(LLM)在信息提取和摘要方面表现出色,但它们恢复潜在科学共识的能力仍不清楚。本文以凝聚态物理中长期存在且备受争议的高温超导(HTS)问题为挑战性测试平台,研究了这一问题。利用过去七十年间近18,000篇高被引出版物,我们构建了一个结构化的知识图谱,链接了竞争性的超导机制、材料家族、证据模态和引用关系。我们发现,LLM提取的表征恢复出了连贯且物理可解释的结构,包括家族依赖的机制概况、证据特定的相关性以及引用介导的科学信念的时间演化。对LLM的消融研究进一步表明,全局结构在提示、解码和模型变化下保持稳健。我们的结果表明,LLM确实可以作为可扩展的工具,用于解读以竞争性解释和知识演变为特征的领域的科学知识。

英文摘要:

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.

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。

↑