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 2312.06185cs.CLcs.AI
收藏

KnowGPT:基于知识图谱的大型语言模型提示

KnowGPT: Knowledge Graph based Prompting for Large Language Models

The Hong Kong Polytechnic University(香港理工大学);Rice University(莱斯大学);Zhejiang Lab(之江实验室)

Qinggang Zhang, Junnan Dong, Hao Chen, Daochen Zha, Zailiang Yu, Xiao Huang

AI总结:

本文提出KnowGPT框架,通过知识提取和上下文感知提示构建模块将知识图谱集成到闭源LLMs中,在三个基准上显著优于竞争方法,OpenbookQA准确率达92.6%。

摘要:

大型语言模型(LLMs)在许多实际应用中展现了卓越的能力。然而,LLMs常因产生幻觉而受到批评,即模型在超出其知识和感知范围的任务上捏造错误陈述。为缓解此问题,研究人员探索利用知识图谱(KGs)中的事实知识,将LLM的响应建立在既定事实和原理之上。然而,大多数最先进的LLMs是闭源的,这使得开发一个仅使用硬提示即可高效有效地将KGs集成到LLMs中的提示框架具有挑战性。通常,现有的KG增强型LLMs存在三个关键问题,包括巨大的搜索空间、高昂的API成本和费力的提示工程,这阻碍了它们在实际中的广泛应用。为此,我们引入了一种新颖的基于知识图谱的提示框架,即KnowGPT,以用领域知识增强LLMs。KnowGPT包含一个知识提取模块,用于从KGs中提取最具信息量的知识,以及一个上下文感知的提示构建模块,用于自动将提取的知识转换为有效的提示。在三个基准上的实验表明,KnowGPT显著优于所有竞争者。值得注意的是,KnowGPT在OpenbookQA排行榜上达到了92.6%的准确率,与人类水平的表现相当。

英文摘要:

Large Language Models (LLMs) have demonstrated remarkable capabilities in many real-world applications. Nonetheless, LLMs are often criticized for their tendency to produce hallucinations, wherein the models fabricate incorrect statements on tasks beyond their knowledge and perception. To alleviate this issue, researchers have explored leveraging the factual knowledge in knowledge graphs (KGs) to ground the LLM's responses in established facts and principles. However, most state-of-the-art LLMs are closed-source, making it challenging to develop a prompting framework that can efficiently and effectively integrate KGs into LLMs with hard prompts only. Generally, existing KG-enhanced LLMs usually suffer from three critical issues, including huge search space, high API costs, and laborious prompt engineering, that impede their widespread application in practice. To this end, we introduce a novel Knowledge Graph based PrompTing framework, namely KnowGPT, to enhance LLMs with domain knowledge. KnowGPT contains a knowledge extraction module to extract the most informative knowledge from KGs, and a context-aware prompt construction module to automatically convert extracted knowledge into effective prompts. Experiments on three benchmarks demonstrate that KnowGPT significantly outperforms all competitors. Notably, KnowGPT achieves a 92.6% accuracy on OpenbookQA leaderboard, comparable to human-level performance.

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。

↑