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 2310.17892astro-ph.IM
收藏

基于大语言模型的天体物理期刊文章中的天文知识实体抽取

Astronomical Knowledge Entity Extraction in Astrophysics Journal Articles via Large Language Models

Wujun Shao, Pengli Ji, Dongwei Fan, Yaohua Hu, Xiaoran Yan, Chenzhou Cui, Linying Mi, Lang Chen, Rui Zhang

AI总结:

本文提出Prompt-KEE提示策略,利用Llama-2-70B、GPT-3.5、GPT-4和Claude 2等大语言模型从天文期刊文章中抽取天体目标标识符和望远镜名称,验证了LLMs在天文知识实体抽取任务中的有效性并分析了影响因素。

摘要:

天文知识实体,如天体目标标识符,对于天文学领域的文献检索、知识图谱构建以及其他研究和应用至关重要。传统的从文本中抽取知识实体的方法面临人工工作量大、泛化能力差和维护成本高等挑战。因此,迫切需要改进方法以高效地抽取这些实体。本研究探索了预训练大语言模型(LLMs)利用提示从天体物理期刊文章中执行天文知识实体抽取(KEE)任务的潜力。我们提出了一种名为Prompt-KEE的提示策略,该策略包含五个提示要素,并基于这些要素设计了八种组合提示。选择天体目标标识符和望远镜名称这两类最典型的天文知识实体作为实验对象。我们引入了四种当前具有代表性的LLMs,即Llama-2-70B、GPT-3.5、GPT-4和Claude 2。为适应它们的token限制,我们构建了两个数据集:30篇文章的全文和段落集合。利用这八种提示,我们在全文上使用GPT-4和Claude 2进行测试,在段落集合上使用所有LLMs进行测试。实验结果表明,预训练LLMs在天体物理期刊文章中执行KEE任务具有显著潜力,但它们的性能存在差异。此外,我们分析了影响LLMs在实体抽取中性能的一些重要因素,并为未来使用LLMs进行天体物理文章KEE任务提供了见解。

英文摘要:

Astronomical knowledge entities, such as celestial object identifiers, are crucial for literature retrieval and knowledge graph construction, and other research and applications in the field of astronomy. Traditional methods of extracting knowledge entities from texts face challenges like high manual effort, poor generalization, and costly maintenance. Consequently, there is a pressing need for improved methods to efficiently extract them. This study explores the potential of pre-trained Large Language Models (LLMs) to perform astronomical knowledge entity extraction (KEE) task from astrophysical journal articles using prompts. We propose a prompting strategy called Prompt-KEE, which includes five prompt elements, and design eight combination prompts based on them. Celestial object identifier and telescope name, two most typical astronomical knowledge entities, are selected to be experimental object. And we introduce four currently representative LLMs, namely Llama-2-70B, GPT-3.5, GPT-4, and Claude 2. To accommodate their token limitations, we construct two datasets: the full texts and paragraph collections of 30 articles. Leveraging the eight prompts, we test on full texts with GPT-4 and Claude 2, on paragraph collections with all LLMs. The experimental results demonstrated that pre-trained LLMs have the significant potential to perform KEE tasks in astrophysics journal articles, but there are differences in their performance. Furthermore, we analyze some important factors that influence the performance of LLMs in entity extraction and provide insights for future KEE tasks in astrophysical articles using LLMs.

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。

↑