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 2402.00414cs.CLcs.AI
收藏

大语言模型的提示时符号知识捕获

Prompt-Time Symbolic Knowledge Capture with Large Language Models

Haltia, Inc.(哈尔蒂亚公司)

Tolga Çöplü, Arto Bendiken, Andrii Skomorokhov, Eduard Bateiko, Stephen Cobb, Joshua J. Bouw

AI总结:

针对大语言模型缺乏提示驱动知识捕获机制的问题,本文聚焦知识图谱场景,通过提示到三元组生成任务探索零样本、少样本提示及微调三种方法,用合成数据集评估性能并公开了代码与数据。

摘要:

为大语言模型(LLMs)增强用户特定知识对个人AI助手等实际应用至关重要,但LLM本身缺乏由提示驱动的知识捕获机制。本文研究利用LLM的现有能力实现提示驱动的知识捕获,重点关注知识图谱。我们通过聚焦提示到三元组(P2T)生成来应对这一挑战,探索了零样本提示、少样本提示和微调三种方法,并通过专门的合成数据集评估其性能。我们的代码和数据集已在https://github.com/HaltiaAI/paper-PTSKC 公开。

英文摘要:

Augmenting large language models (LLMs) with user-specific knowledge is crucial for real-world applications, such as personal AI assistants. However, LLMs inherently lack mechanisms for prompt-driven knowledge capture. This paper investigates utilizing the existing LLM capabilities to enable prompt-driven knowledge capture, with a particular emphasis on knowledge graphs. We address this challenge by focusing on prompt-to-triple (P2T) generation. We explore three methods: zero-shot prompting, few-shot prompting, and fine-tuning, and then assess their performance via a specialized synthetic dataset. Our code and datasets are publicly available at https://github.com/HaltiaAI/paper-PTSKC.

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。

↑