A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy
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_ | 1866910988599558144 |
|---|---|
| author | Zhao, Yang Dai, Chengxiao Niyato, Dusit Tan, Chuan Fu Xiang, Keyi Wang, Yueyang Yeo, Zhiquan Loong, Daren Tan Zong Zhaozhi, Jonathan Low HO, Eugene H. Z. |
| author_facet | Zhao, Yang Dai, Chengxiao Niyato, Dusit Tan, Chuan Fu Xiang, Keyi Wang, Yueyang Yeo, Zhiquan Loong, Daren Tan Zong Zhaozhi, Jonathan Low HO, Eugene H. Z. |
| contents | Large language models (LLMs) hold promise for sustainable manufacturing, but often hallucinate industrial codes and emission factors, undermining regulatory and investment decisions. We introduce CircuGraphRAG, a retrieval-augmented generation (RAG) framework that grounds LLMs outputs in a domain-specific knowledge graph for the circular economy. This graph connects 117,380 industrial and waste entities with classification codes and GWP100 emission data, enabling structured multi-hop reasoning. Natural language queries are translated into SPARQL and verified subgraphs are retrieved to ensure accuracy and traceability. Compared with Standalone LLMs and Naive RAG, CircuGraphRAG achieves superior performance in single-hop and multi-hop question answering, with ROUGE-L F1 scores up to 1.0, while baseline scores below 0.08. It also improves efficiency, halving the response time and reducing token usage by 16% in representative tasks. CircuGraphRAG provides fact-checked, regulatory-ready support for circular economy planning, advancing reliable, low-carbon resource decision making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_04252 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy Zhao, Yang Dai, Chengxiao Niyato, Dusit Tan, Chuan Fu Xiang, Keyi Wang, Yueyang Yeo, Zhiquan Loong, Daren Tan Zong Zhaozhi, Jonathan Low HO, Eugene H. Z. Artificial Intelligence Computation and Language Machine Learning Large language models (LLMs) hold promise for sustainable manufacturing, but often hallucinate industrial codes and emission factors, undermining regulatory and investment decisions. We introduce CircuGraphRAG, a retrieval-augmented generation (RAG) framework that grounds LLMs outputs in a domain-specific knowledge graph for the circular economy. This graph connects 117,380 industrial and waste entities with classification codes and GWP100 emission data, enabling structured multi-hop reasoning. Natural language queries are translated into SPARQL and verified subgraphs are retrieved to ensure accuracy and traceability. Compared with Standalone LLMs and Naive RAG, CircuGraphRAG achieves superior performance in single-hop and multi-hop question answering, with ROUGE-L F1 scores up to 1.0, while baseline scores below 0.08. It also improves efficiency, halving the response time and reducing token usage by 16% in representative tasks. CircuGraphRAG provides fact-checked, regulatory-ready support for circular economy planning, advancing reliable, low-carbon resource decision making. |
| title | A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy |
| topic | Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2506.04252 |