Prompt-Time Symbolic Knowledge Capture with Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909090065678336 |
|---|---|
| author | Çöplü, Tolga Bendiken, Arto Skomorokhov, Andrii Bateiko, Eduard Cobb, Stephen Bouw, Joshua J. |
| author_facet | Çöplü, Tolga Bendiken, Arto Skomorokhov, Andrii Bateiko, Eduard Cobb, Stephen Bouw, Joshua J. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_00414 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Prompt-Time Symbolic Knowledge Capture with Large Language Models Çöplü, Tolga Bendiken, Arto Skomorokhov, Andrii Bateiko, Eduard Cobb, Stephen Bouw, Joshua J. Computation and Language Artificial Intelligence I.2.7 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. |
| title | Prompt-Time Symbolic Knowledge Capture with Large Language Models |
| topic | Computation and Language Artificial Intelligence I.2.7 |
| url | https://arxiv.org/abs/2402.00414 |