Prompt-Time Ontology-Driven 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_ | 1866914807517544448 |
|---|---|
| author | Çöplü, Tolga Bendiken, Arto Skomorokhov, Andrii Bateiko, Eduard Cobb, Stephen |
| author_facet | Çöplü, Tolga Bendiken, Arto Skomorokhov, Andrii Bateiko, Eduard Cobb, Stephen |
| contents | In applications such as personal assistants, large language models (LLMs) must consider the user's personal information and preferences. However, LLMs lack the inherent ability to learn from user interactions. This paper explores capturing personal information from user prompts using ontology and knowledge-graph approaches. We use a subset of the KNOW ontology, which models personal information, to train the language model on these concepts. We then evaluate the success of knowledge capture using a specially constructed dataset. Our code and datasets are publicly available at https://github.com/HaltiaAI/paper-PTODSKC |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_14012 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Prompt-Time Ontology-Driven Symbolic Knowledge Capture with Large Language Models Çöplü, Tolga Bendiken, Arto Skomorokhov, Andrii Bateiko, Eduard Cobb, Stephen Artificial Intelligence Computation and Language I.2.7 In applications such as personal assistants, large language models (LLMs) must consider the user's personal information and preferences. However, LLMs lack the inherent ability to learn from user interactions. This paper explores capturing personal information from user prompts using ontology and knowledge-graph approaches. We use a subset of the KNOW ontology, which models personal information, to train the language model on these concepts. We then evaluate the success of knowledge capture using a specially constructed dataset. Our code and datasets are publicly available at https://github.com/HaltiaAI/paper-PTODSKC |
| title | Prompt-Time Ontology-Driven Symbolic Knowledge Capture with Large Language Models |
| topic | Artificial Intelligence Computation and Language I.2.7 |
| url | https://arxiv.org/abs/2405.14012 |