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 2310.14029cs.CLcond-mat.mtrl-sci
收藏

LLM-Prop:从晶体固体的文本描述预测其物理与电子性质

LLM-Prop: Predicting Physical And Electronic Properties Of Crystalline Solids From Their Text Descriptions

Princeton University(普林斯顿大学);Vertaix

Andre Niyongabo Rubungo, Craig Arnold, Barry P. Rand, Adji Bousso Dieng

AI总结:

本文提出LLM-Prop方法,利用大语言模型从晶体文本描述预测其物理与电子性质,并公开了TextEdge基准数据集,实验表明其性能优于现有GNN模型。

摘要:

晶体性质的预测在晶体设计过程中起着至关重要的作用。当前预测晶体性质的方法侧重于使用图神经网络(GNNs)对晶体结构进行建模。尽管GNNs功能强大,但准确建模晶体内原子和分子之间的复杂相互作用仍然是一个挑战。令人惊讶的是,尽管文本数据提供了丰富的信息和表达能力,但从晶体文本描述预测晶体性质的研究仍然不足。主要原因之一是缺乏用于该任务的公开可用数据。在本文中,我们开发并公开了一个基准数据集(称为TextEdge),其中包含晶体结构的文本描述及其性质。然后,我们提出了LLM-Prop,这是一种利用大型语言模型(LLMs)的通用学习能力,从晶体文本描述预测晶体物理和电子性质的方法。LLM-Prop在预测带隙方面比当前最先进的基于GNN的晶体性质预测器高出约4%,在分类带隙是直接还是间接方面高出3%,在预测晶胞体积方面高出66%。尽管参数量少了3倍,LLM-Prop的表现也优于经过微调的MatBERT(一种特定领域的预训练BERT模型)。我们的实证结果可能突显了当前GNNs在捕获与空间群对称性和Wyckoff位点相关的信息以进行准确晶体性质预测方面的不足。

英文摘要:

The prediction of crystal properties plays a crucial role in the crystal design process. Current methods for predicting crystal properties focus on modeling crystal structures using graph neural networks (GNNs). Although GNNs are powerful, accurately modeling the complex interactions between atoms and molecules within a crystal remains a challenge. Surprisingly, predicting crystal properties from crystal text descriptions is understudied, despite the rich information and expressiveness that text data offer. One of the main reasons is the lack of publicly available data for this task. In this paper, we develop and make public a benchmark dataset (called TextEdge) that contains text descriptions of crystal structures with their properties. We then propose LLM-Prop, a method that leverages the general-purpose learning capabilities of large language models (LLMs) to predict the physical and electronic properties of crystals from their text descriptions. LLM-Prop outperforms the current state-of-the-art GNN-based crystal property predictor by about 4% in predicting band gap, 3% in classifying whether the band gap is direct or indirect, and 66% in predicting unit cell volume. LLM-Prop also outperforms a finetuned MatBERT, a domain-specific pre-trained BERT model, despite having 3 times fewer parameters. Our empirical results may highlight the current inability of GNNs to capture information pertaining to space group symmetry and Wyckoff sites for accurate crystal property prediction.

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。

↑