基于动态少样本学习的大语言模型预测双钙钛矿的空间群
Predicting Space Groups of Double Perovskites by LLM with Dynamic Few-Shot Learning
浏览论文内容
中文总结 AI 辅助
该研究提出基于LLM智能体的DyRIS框架，通过动态少样本检索与规则引导推理，在不平衡双钙钛矿数据集上提升了空间群预测的整体及少数类性能，验证了领域知识与LLM结合的有效性。
中文摘要 AI 辅助
双钙钛矿（DPs）具有广泛的成分可调性，但预测稳定结构的空间群（SGs）仍然困难，因为现有数据集通常对主要SG类别存在严重的类别不平衡问题。我们将主要SG类别称为major SGs，将代表性不足的类别称为minor SGs。我们引入了用于空间群预测的动态且多样性增强的少样本检索与规则引导推理框架（DyRIS），这是一个基于大语言模型智能体的框架，可根据给定的DP成分预测排名的SG候选。DyRIS使用多样性增强的动态少样本提示来检索相关的上下文示例，同时限制频繁出现的SGs的主导地位。它还结合了基于B/B'阳离子有序性、定量指标和major SG偏差控制的规则引导推理，以优化并排名最终的Top-3 SG候选。我们在3528个经过热力学筛选的DP条目上评估DyRIS，并将其与基于成分和基于描述符的基线进行比较。在训练数据比例为0.5时，DyRIS实现了有竞争力的整体准确率，同时获得了最佳的整体Top-1 macro-F1得分和所有minor SG指标上的最佳性能。DyRIS相对于CrabNet将minor SG Top-1准确率提高了3.26个百分点，并且比最强的基于PyCaret的基线实现了更高的minor SG Top-3准确率。 ablation研究表明，多样性增强检索、定量指标、major SG偏差控制和B/B'有序性信息均对预测性能有贡献。额外实验表明，最终的规则引导推理步骤难以被传统的分类器或排序器模型替代。这些发现证明了将基于检索的大语言模型推理与晶体学领域知识相结合，用于不平衡材料数据集的SG预测的潜力。
英文摘要
Double perovskites (DPs) offer broad compositional tunability, but predicting the space groups (SGs) of stable structures remains difficult because available datasets are often strongly imbalanced toward dominant SG classes. We refer to dominant SG classes as major SGs and underrepresented classes as minor SGs. We introduce Dynamic and Diversity-enhanced Few-shot Retrieval and Rule-Guided Inference for Space-Group Prediction (DyRIS), an LLM-agent-based framework that predicts ranked SG candidates from a given DP composition. DyRIS uses diversity-enhanced dynamic few-shot prompting to retrieve relevant in-context examples while limiting the dominance of frequently represented SGs. It further incorporates rule-guided inference based on B/B' cation ordering, quantitative indicators, and major-SG bias control to refine and rank the final Top-3 SG candidates. We evaluate DyRIS on 3,528 thermodynamically filtered DP entries and compare it with composition-based and descriptor-based baselines. At a training-data ratio of 0.5, DyRIS achieves competitive overall accuracy while obtaining the best Overall Top-1 macro-F1 score and the best performance across all Minor-SG metrics. DyRIS improves Minor-SG Top-1 accuracy by 3.26 percentage points relative to CrabNet and achieves higher Minor-SG Top-3 accuracy than the strongest PyCaret-based baseline. Ablation studies show that diversity-enhanced retrieval, quantitative indicators, major-SG bias control, and B/B' ordering information each contribute to prediction performance. Additional experiments show that the final rule-guided inference step is not easily replaced by conventional classifier- or ranker-based models. These findings demonstrate the potential of combining retrieval-based LLM reasoning with crystallographic domain knowledge for SG prediction in imbalanced materials datasets.
