使用对话模型进行数据提取和材料性质预测的动态上下文学习
Dynamic In-context Learning with Conversational Models for Data Extraction and Materials Property Prediction
AI总结：
本文提出开源工具 PropertyExtractor，结合对话式 LLM、零样本/少样本上下文学习和工程化提示，实现可信的材料性质提取与验证，并构建二维材料厚度和能带隙数据库。
摘要：
自然语言处理和大型语言模型（LLM）的出现，已经彻底改变了从非结构化学术论文中提取数据的方式。然而，确保数据可信度仍然是一项重大挑战。本文介绍了开源工具 PropertyExtractor，它利用 Google gemini-pro 和 OpenAI gpt-4 等先进对话式 LLM，将零样本与少样本上下文学习相结合，并采用工程化提示对结构化信息层级进行动态细化，从而实现自主、高效、可扩展且准确的材料性质数据识别、提取与验证。我们在材料数据上的测试表明，精确率和召回率均超过 95%，错误率约为 9%，凸显了该工具包的有效性和多功能性。最后，使用 PropertyExtractor 建立了二维材料厚度（器件集成的关键参数）数据库和能带隙值数据库。特别是对于厚度数据库，该领域的快速发展已经超过实验测量和计算方法，形成了显著的数据空白。我们的工作填补了这一空白，并展示了 PropertyExtractor 作为可靠、高效工具自主生成各类材料性质数据库、推动该领域发展的潜力。
英文摘要：
The advent of natural language processing and large language models (LLMs) has revolutionized the extraction of data from unstructured scholarly papers. However, ensuring data trustworthiness remains a significant challenge. In this paper, we introduce PropertyExtractor, an open-source tool that leverages advanced conversational LLMs like Google gemini-pro and OpenAI gpt-4, blends zero-shot with few-shot in-context learning, and employs engineered prompts for the dynamic refinement of structured information hierarchies - enabling autonomous, efficient, scalable, and accurate identification, extraction, and verification of material property data. Our tests on material data demonstrate precision and recall that exceed 95\% with an error rate of approximately 9%, highlighting the effectiveness and versatility of the toolkit. Finally, databases for 2D material thicknesses, a critical parameter for device integration, and energy bandgap values are developed using PropertyExtractor. Specifically for the thickness database, the rapid evolution of the field has outpaced both experimental measurements and computational methods, creating a significant data gap. Our work addresses this gap and showcases the potential of PropertyExtractor as a reliable and efficient tool for the autonomous generation of various material property databases, advancing the field.
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。
