从科学文献中自动提取网状材料合成细节的LLM方法
Automated, LLM enabled extraction of synthesis details for reticular materials from scientific literature
AI总结：
本文提出知识提取流水线（KEP），利用开源大语言模型结合上下文学习，无需微调即可从文献中自动提取网状材料合成方案，减少人工标注。
摘要：
从科学文献中自动提取知识有可能加速材料发现。我们研究了一种使用大型语言模型（LLMs）从科学文献中提取网状材料合成方案的方法。为此，我们引入了一个知识提取流水线（KEP），该流水线自动化了LLM辅助的段落分类和信息提取。通过对一组开源LLMs应用带有上下文学习（ICL）的提示工程，我们证明了LLMs可以从PDF文档中检索化学信息，而无需微调或训练，并且降低了幻觉风险。通过比较五个开源LLM系列在段落分类和信息提取任务中的性能，我们观察到即使ICL提示中只包含少量示例段落，模型性能也非常出色。结果表明，KEP方法在减少自动化科学知识提取中的人工标注和数据整理工作方面具有潜力。
英文摘要：
Automated knowledge extraction from scientific literature can potentially accelerate materials discovery. We have investigated an approach for extracting synthesis protocols for reticular materials from scientific literature using large language models (LLMs). To that end, we introduce a Knowledge Extraction Pipeline (KEP) that automatizes LLM-assisted paragraph classification and information extraction. By applying prompt engineering with in-context learning (ICL) to a set of open-source LLMs, we demonstrate that LLMs can retrieve chemical information from PDF documents, without the need for fine-tuning or training and at a reduced risk of hallucination. By comparing the performance of five open-source families of LLMs in both paragraph classification and information extraction tasks, we observe excellent model performance even if only few example paragraphs are included in the ICL prompts. The results show the potential of the KEP approach for reducing human annotations and data curation efforts in automated scientific knowledge extraction.
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。
