Lifen Sun
Lifen Sun has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Da Long
Merck Holding (China) Co., Ltd., Shanghai, People’s Republic of China
2 shared publications - Tian Li
Merck Holding (China) Co., Ltd., Shanghai, China, China
1 shared publication - Tian Li
Merck Holding (China) Co., Ltd., Shanghai, People’s Republic of China
1 shared publication - Yabo Wang
Merck Holding (China) Co., Ltd., Shanghai, China, China
1 shared publication - Yabo Wang
Merck Holding (China) Co., Ltd., Shanghai, People’s Republic of China
1 shared publication
Latest Publications
- Open Access
- 1 March 2026
- Published by IOP Publishing in AI for Science
- Vol. 2 (1) , 015003
Jigsaw-like knowledge graph generation: a study on generalization patterns with a LightRAG implementation
The integration of knowledge graphs (KGs) with retrieval-augmented generation (RAG) has significantly advanced domain-specific question-answering systems. However, a critical limitation persists in existing KG-based RAG frameworks: the inability to efficiently handle localized updates within a dynamic document corpus. Current methods typically necessitate a complete KG rebuild for even minor changes, leading to prohibitive computational costs of large language model (LLM) token consumption and significant KG generation time expenditure. To address this, we propose a novel jigsaw-like methodology from subgraphs to global KG generation and maintenance. Our approach leverages document lifecycle states (new, modified, persistent, deleted) to isolate and process only the ‘delta changes’ within the corpus. By decomposing the KG into document-level subgraphs, we enable token-efficient, localized updates where LLM extraction is invoked solely for altered documents, while reusing subgraphs from unchanged content. We engineer and evaluate Jigsaw-LightRAG, an extension of the vanilla LightRAG framework that implements this algorithm. Extensive experiments on public datasets demonstrate that this new framework reduces LLM token consumption by orders of magnitude during incremental updates while maintaining the structural integrity of the KG and achieving performance parity with full-rebuild baselines on question answering tasks. This work provides a computationally efficient and robust solution for dynamic AI knowledge base management, offering substantial practical value for applications requiring frequent KG updates.
- 1 March 2026
- Published by IOP Publishing in AI for Science
- Vol. 2 (1) , 015003
Open AccessJigsaw-like knowledge graph generation: a study on generalization patterns with a LightRAG implementation
The integration of knowledge graphs (KGs) with retrieval-augmented generation (RAG) has significantly advanced domain-specific question-answering systems. However, a critical limitation persists in existing KG-based RAG frameworks: the inability to efficiently handle localized updates within a dynamic document corpus. Current methods typically necessitate a complete KG rebuild for even minor changes, leading to prohibitive computational costs of large language model (LLM) token consumption and significant KG generation time expenditure. To address this, we propose a novel jigsaw-like methodology from subgraphs to global KG generation and maintenance. Our approach leverages document lifecycle states (new, modified, persistent, deleted) to isolate and process only the ‘delta changes’ within the corpus. By decomposing the KG into document-level subgraphs, we enable token-efficient, localized updates where LLM extraction is invoked solely for altered documents, while reusing subgraphs from unchanged content. We engineer and evaluate Jigsaw-LightRAG, an extension of the vanilla LightRAG framework that implements this algorithm. Extensive experiments on public datasets demonstrate that this new framework reduces LLM token consumption by orders of magnitude during incremental updates while maintaining the structural integrity of the KG and achieving performance parity with full-rebuild baselines on question answering tasks. This work provides a computationally efficient and robust solution for dynamic AI knowledge base management, offering substantial practical value for applications requiring frequent KG updates.
- Open Access
- 14 November 2025
- Published by MDPI AG in Preprints.org
Jigsaw-Like Knowledge Graph Generation: A Study on Generalization Patterns with a LightRAG Implementation
The integration of knowledge graphs (KGs) with Retrieval-Augmented Generation (RAG) has significantly advanced domain-specific question-answering systems. However, a critical limitation persists in existing KG-based RAG frameworks: the inability to efficiently handle localized updates within a dynamic document corpus. Current methods typically necessitate a complete KG rebuild for even minor changes, leading to prohibitive computational costs of large language model (LLM) token consumption and significant KG generation time expenditure. To address this, we propose a novel jigsaw-like methodology from subgraphs to global KG generation and maintenance. Our approach leverages document lifecycle states (new, modified, persistent, deleted) to isolate and process only the 'delta changes' within the corpus. By decomposing the KG into document-level subgraphs, we enable token-efficient, localized updates where LLM extraction is invoked solely for altered documents, while reusing subgraphs from unchanged content. We engineer and evaluate Jigsaw-LightRAG, an extension of the vanilla LightRAG framework that implements this algorithm. Extensive experiments on public datasets demonstrate that this new framework reduces LLM token consumption by orders of magnitude during incremental updates while maintaining the structural integrity of the KG and achieving performance parity with full-rebuild baselines on question answering (QA) tasks. This work provides a computationally efficient and robust solution for dynamic AI knowledge base management, offering substantial practical value for applications requiring frequent KG updates.
- 14 November 2025
- Published by MDPI AG in Preprints.org
Open AccessJigsaw-Like Knowledge Graph Generation: A Study on Generalization Patterns with a LightRAG Implementation
The integration of knowledge graphs (KGs) with Retrieval-Augmented Generation (RAG) has significantly advanced domain-specific question-answering systems. However, a critical limitation persists in existing KG-based RAG frameworks: the inability to efficiently handle localized updates within a dynamic document corpus. Current methods typically necessitate a complete KG rebuild for even minor changes, leading to prohibitive computational costs of large language model (LLM) token consumption and significant KG generation time expenditure. To address this, we propose a novel jigsaw-like methodology from subgraphs to global KG generation and maintenance. Our approach leverages document lifecycle states (new, modified, persistent, deleted) to isolate and process only the 'delta changes' within the corpus. By decomposing the KG into document-level subgraphs, we enable token-efficient, localized updates where LLM extraction is invoked solely for altered documents, while reusing subgraphs from unchanged content. We engineer and evaluate Jigsaw-LightRAG, an extension of the vanilla LightRAG framework that implements this algorithm. Extensive experiments on public datasets demonstrate that this new framework reduces LLM token consumption by orders of magnitude during incremental updates while maintaining the structural integrity of the KG and achieving performance parity with full-rebuild baselines on question answering (QA) tasks. This work provides a computationally efficient and robust solution for dynamic AI knowledge base management, offering substantial practical value for applications requiring frequent KG updates.