Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915129261555712 |
|---|---|
| author | Lin, Qika Zhao, Tianzhe He, Kai Peng, Zhen Xu, Fangzhi Huang, Ling Ma, Jingying Feng, Mengling |
| author_facet | Lin, Qika Zhao, Tianzhe He, Kai Peng, Zhen Xu, Fangzhi Huang, Ling Ma, Jingying Feng, Mengling |
| contents | Due to the presence of the natural gap between Knowledge Graph (KG) structures and the natural language, the effective integration of holistic structural information of KGs with Large Language Models (LLMs) has emerged as a significant question. To this end, we propose a two-stage framework to learn and apply quantized codes for each entity, aiming for the seamless integration of KGs with LLMs. Firstly, a self-supervised quantized representation (SSQR) method is proposed to compress both KG structural and semantic knowledge into discrete codes (\ie, tokens) that align the format of language sentences. We further design KG instruction-following data by viewing these learned codes as features to directly input to LLMs, thereby achieving seamless integration. The experiment results demonstrate that SSQR outperforms existing unsupervised quantized methods, producing more distinguishable codes. Further, the fine-tuned LLaMA2 and LLaMA3.1 also have superior performance on KG link prediction and triple classification tasks, utilizing only 16 tokens per entity instead of thousands in conventional prompting methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_18119 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models Lin, Qika Zhao, Tianzhe He, Kai Peng, Zhen Xu, Fangzhi Huang, Ling Ma, Jingying Feng, Mengling Computation and Language Artificial Intelligence Due to the presence of the natural gap between Knowledge Graph (KG) structures and the natural language, the effective integration of holistic structural information of KGs with Large Language Models (LLMs) has emerged as a significant question. To this end, we propose a two-stage framework to learn and apply quantized codes for each entity, aiming for the seamless integration of KGs with LLMs. Firstly, a self-supervised quantized representation (SSQR) method is proposed to compress both KG structural and semantic knowledge into discrete codes (\ie, tokens) that align the format of language sentences. We further design KG instruction-following data by viewing these learned codes as features to directly input to LLMs, thereby achieving seamless integration. The experiment results demonstrate that SSQR outperforms existing unsupervised quantized methods, producing more distinguishable codes. Further, the fine-tuned LLaMA2 and LLaMA3.1 also have superior performance on KG link prediction and triple classification tasks, utilizing only 16 tokens per entity instead of thousands in conventional prompting methods. |
| title | Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2501.18119 |