GraphRAG与多模态知识图谱：研究与应用

参考文献与官方资料

检索截至2026年10月19日。保留原题名与阅读范围；预印本和技术文章的结论须结合原始条件理解。

1. [R01]
   Jonathan Larson and Steven Truitt (2024-02-13). GraphRAG: Unlocking LLM discovery on narrative private dataMicrosoft Research blog · article or documentation content
2. [R02]
   Darren Edge et al. (2024; v2 2025-02-19). From Local to Global: A GraphRAG Approach to Query-Focused SummarizationResearch preprint · abstract and workflow sections
3. [R03]
   美团技术团队 (2024-05-17). 基于多模态信息抽取的菜品知识图谱构建Industry technical article · article or documentation content
4. [R04]
   Lanjun Wang et al. (2024 online; IEEE TMM volume 27 (2025), pp. 2863–2874). Toward Chinese Food Understanding: A Cross-Modal Ingredient-Level BenchmarkIEEE Transactions on Multimedia · abstract or primary publication record
5. [R05]
   CMIngre research team (accessed 2026-10-18). CMIngre Dataset and Supplementary MaterialAuthor dataset · article or documentation content
6. [R06]
   Patrick Lewis et al. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksResearch paper · abstract or primary publication record
7. [R07]
   Boci Peng et al. (2024 preprint; later journal version). Graph Retrieval-Augmented Generation: A SurveySurvey · abstract or primary publication record
8. [R08]
   Haoyu Han et al. (2025 arXiv identifier). Retrieval-Augmented Generation with Graphs (GraphRAG)Survey · abstract or primary publication record
9. [R09]
   Haoyu Han et al. (2025 preprint). RAG vs. GraphRAG: A Systematic Evaluation and Key InsightsComparative study · abstract or primary publication record
10. [R10]
    Zirui Guo et al. (2024 preprint; 2025 EMNLP Findings). LightRAG: Simple and Fast Retrieval-Augmented GenerationResearch paper · abstract or primary publication record
11. [R11]
    Bernal Jiménez Gutiérrez et al. (2024). HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language ModelsResearch paper · abstract or primary publication record
12. [R12]
    Bernal Jiménez Gutiérrez et al. (2025). From RAG to Memory: Non-Parametric Continual Learning for Large Language ModelsHippoRAG 2 research paper · abstract or primary publication record
13. [R13]
    Xiangrong Zhu et al. (2025). Knowledge Graph-Guided Retrieval Augmented GenerationKG2RAG research paper · abstract or primary publication record
14. [R14]
    Xiaoxin He et al. (2024). G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question AnsweringResearch paper · abstract or primary publication record
15. [R15]
    Xiangru Zhu et al. (2022 preprint). Multi-Modal Knowledge Graph Construction and Application: A SurveySurvey · abstract or primary publication record
16. [R16]
    Zhuo Chen et al. (2024). Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive SurveySurvey · abstract or primary publication record
17. [R17]
    Alec Radford et al. (2021). Learning Transferable Visual Models From Natural Language SupervisionICML research paper · abstract or primary publication record
18. [R18]
    Wenhu Chen et al. (2022). MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and TextEMNLP research paper · abstract or primary publication record
19. [R19]
    Xueyao Wan and Hang Yu (2025 first version; v3 2026-07-18). MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge GraphsResearch preprint · abstract or primary publication record
20. [R20]
    Xu Yuan, Liangbo Ning, Qingqing Ye, Wenqi Fan and Qing Li (2025 preprint; v2 2026-04-27; SIGIR 2026). mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQASIGIR 2026 paper; inspected arXiv version · abstract or primary publication record
21. [R21]
    Yin Wu, Quanyu Long, Jing Li, Jianfei Yu and Wenya Wang (2025 preprint v2; related SIGIR 2026 Resource Track version). Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive QueriesBenchmark paper; inspected arXiv v2 and author repository · abstract or primary publication record
22. [R22]
    Juyeon Kim, Geon Lee, Taeuk Kim and Kijung Shin (2025). KGMEL: Knowledge Graph-Enhanced Multimodal Entity LinkingSIGIR 2025 short paper; inspected arXiv record · abstract or primary publication record
23. [R23]
    Manuel Faysse et al. (2024). ColPali: Efficient Document Retrieval with Vision Language ModelsResearch paper · abstract or primary publication record
24. [R24]
    Zirui Guo et al. (2025). RAG-Anything: All-in-One RAG FrameworkResearch preprint · abstract or primary publication record
25. [R25]
    Shahul Es et al. (2024). RAGAs: Automated Evaluation of Retrieval Augmented GenerationEACL System Demonstrations · abstract or primary publication record
26. [R26]
    Hao Yu et al. (2024). Evaluation of Retrieval-Augmented Generation: A SurveySurvey preprint · abstract or primary publication record
27. [R27]
    V. A. Traag, L. Waltman and N. J. van Eck (2019). From Louvain to Leiden: guaranteeing well-connected communitiesScientific Reports · abstract or primary publication record
28. [R28]
    W3C (2013). PROV OverviewW3C Working Group Note · abstract or primary publication record
29. [R29]
    Nelson F. Liu et al. (2023 preprint). Lost in the Middle: How Language Models Use Long ContextsResearch paper · abstract or primary publication record
30. [R30]
    Alon Talmor et al. (2021). MultiModalQA: Complex Question Answering over Text, Tables and ImagesBenchmark paper · abstract or primary publication record
31. [R31]
    Yingshan Chang et al. (2021 preprint; CVPR 2022). WebQA: Multihop and Multimodal QABenchmark paper · abstract or primary publication record
32. [R32]
    Microsoft (accessed 2026-10-18). GraphRAG Indexing DataflowOfficial documentation · article or documentation content
33. [R33]
    Microsoft (accessed 2026-10-18). GraphRAG Global SearchOfficial documentation · article or documentation content