KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916135138492416 |
|---|---|
| author | Wei, Yanbin Huang, Qiushi Kwok, James T. Zhang, Yu |
| author_facet | Wei, Yanbin Huang, Qiushi Kwok, James T. Zhang, Yu |
| contents | Knowledge Graph Completion (KGC) is crucial for addressing knowledge graph incompleteness and supporting downstream applications. Many models have been proposed for KGC. They can be categorized into two main classes: triple-based and text-based approaches. Triple-based methods struggle with long-tail entities due to limited structural information and imbalanced entity distributions. Text-based methods alleviate this issue but require costly training for language models and specific finetuning for knowledge graphs, which limits their efficiency. To alleviate these limitations, in this paper, we propose KICGPT, a framework that integrates a large language model (LLM) and a triple-based KGC retriever. It alleviates the long-tail problem without incurring additional training overhead. KICGPT uses an in-context learning strategy called Knowledge Prompt, which encodes structural knowledge into demonstrations to guide the LLM. Empirical results on benchmark datasets demonstrate the effectiveness of KICGPT with smaller training overhead and no finetuning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_02389 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion Wei, Yanbin Huang, Qiushi Kwok, James T. Zhang, Yu Computation and Language Artificial Intelligence Knowledge Graph Completion (KGC) is crucial for addressing knowledge graph incompleteness and supporting downstream applications. Many models have been proposed for KGC. They can be categorized into two main classes: triple-based and text-based approaches. Triple-based methods struggle with long-tail entities due to limited structural information and imbalanced entity distributions. Text-based methods alleviate this issue but require costly training for language models and specific finetuning for knowledge graphs, which limits their efficiency. To alleviate these limitations, in this paper, we propose KICGPT, a framework that integrates a large language model (LLM) and a triple-based KGC retriever. It alleviates the long-tail problem without incurring additional training overhead. KICGPT uses an in-context learning strategy called Knowledge Prompt, which encodes structural knowledge into demonstrations to guide the LLM. Empirical results on benchmark datasets demonstrate the effectiveness of KICGPT with smaller training overhead and no finetuning. |
| title | KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2402.02389 |