Review of key technologies in knowledge graphs powered by code large language models
Traditional knowledge graph technologies still face significant challenges in converting human knowledge, expressed in natural language, into a formal language-based knowledge graph and utilizing it effectively. In recent years, code large language models (LLMs) have demonstrated remarkable capabili...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
China InfoCom Media Group
2025-03-01
|
| Series: | 大数据 |
| Subjects: | |
| Online Access: | http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2025022 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850140687792603136 |
|---|---|
| author | LI Zixuan BAI Long REN Weicheng SU Miao LIU Wenxuan CHEN Lei³ JIN Xiaolong |
| author_facet | LI Zixuan BAI Long REN Weicheng SU Miao LIU Wenxuan CHEN Lei³ JIN Xiaolong |
| author_sort | LI Zixuan |
| collection | DOAJ |
| description | Traditional knowledge graph technologies still face significant challenges in converting human knowledge, expressed in natural language, into a formal language-based knowledge graph and utilizing it effectively. In recent years, code large language models (LLMs) have demonstrated remarkable capabilities in understanding both natural and formal languages, as well as in translating between them. These advancements are expected to drive significant breakthroughs in developing next-generation knowledge graph technologies. This paper reviews the application of code LLMs in KGs. Firstly, this paper systematically analyzes the role of code LLMs in enhancing key knowledge graph technologies across three critical areas: construction, reasoning, and question-answering. Secondly, a relatively detailed introduction to the existing methodologies in these areas is provided. Finally, this paper summarizes the current state in the field and offers insights into the future of knowledge graph technologies empowered by code LLMs. In the future, knowledge representation based on programming languages is expected to enable more efficient, automated, and complex operations on knowledge graphs, realizing knowledge programming. |
| format | Article |
| id | doaj-art-d9ec6c8cc7914816bcc4a0f4ac2b73f3 |
| institution | OA Journals |
| issn | 2096-0271 |
| language | zho |
| publishDate | 2025-03-01 |
| publisher | China InfoCom Media Group |
| record_format | Article |
| series | 大数据 |
| spelling | doaj-art-d9ec6c8cc7914816bcc4a0f4ac2b73f32025-08-20T02:29:42ZzhoChina InfoCom Media Group大数据2096-02712025-03-0111192886967612Review of key technologies in knowledge graphs powered by code large language modelsLI ZixuanBAI LongREN WeichengSU MiaoLIU WenxuanCHEN Lei³JIN XiaolongTraditional knowledge graph technologies still face significant challenges in converting human knowledge, expressed in natural language, into a formal language-based knowledge graph and utilizing it effectively. In recent years, code large language models (LLMs) have demonstrated remarkable capabilities in understanding both natural and formal languages, as well as in translating between them. These advancements are expected to drive significant breakthroughs in developing next-generation knowledge graph technologies. This paper reviews the application of code LLMs in KGs. Firstly, this paper systematically analyzes the role of code LLMs in enhancing key knowledge graph technologies across three critical areas: construction, reasoning, and question-answering. Secondly, a relatively detailed introduction to the existing methodologies in these areas is provided. Finally, this paper summarizes the current state in the field and offers insights into the future of knowledge graph technologies empowered by code LLMs. In the future, knowledge representation based on programming languages is expected to enable more efficient, automated, and complex operations on knowledge graphs, realizing knowledge programming.http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2025022code large language modellarge language model |
| spellingShingle | LI Zixuan BAI Long REN Weicheng SU Miao LIU Wenxuan CHEN Lei³ JIN Xiaolong Review of key technologies in knowledge graphs powered by code large language models 大数据 code large language model large language model |
| title | Review of key technologies in knowledge graphs powered by code large language models |
| title_full | Review of key technologies in knowledge graphs powered by code large language models |
| title_fullStr | Review of key technologies in knowledge graphs powered by code large language models |
| title_full_unstemmed | Review of key technologies in knowledge graphs powered by code large language models |
| title_short | Review of key technologies in knowledge graphs powered by code large language models |
| title_sort | review of key technologies in knowledge graphs powered by code large language models |
| topic | code large language model large language model |
| url | http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2025022 |
| work_keys_str_mv | AT lizixuan reviewofkeytechnologiesinknowledgegraphspoweredbycodelargelanguagemodels AT bailong reviewofkeytechnologiesinknowledgegraphspoweredbycodelargelanguagemodels AT renweicheng reviewofkeytechnologiesinknowledgegraphspoweredbycodelargelanguagemodels AT sumiao reviewofkeytechnologiesinknowledgegraphspoweredbycodelargelanguagemodels AT liuwenxuan reviewofkeytechnologiesinknowledgegraphspoweredbycodelargelanguagemodels AT chenlei3 reviewofkeytechnologiesinknowledgegraphspoweredbycodelargelanguagemodels AT jinxiaolong reviewofkeytechnologiesinknowledgegraphspoweredbycodelargelanguagemodels |