{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T16:07:39Z","timestamp":1784650059613,"version":"3.55.0"},"reference-count":49,"publisher":"Association for Computing Machinery (ACM)","issue":"2","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGMOD Rec."],"published-print":{"date-parts":[[2026,7,20]]},"abstract":"<jats:p>The integration of large language models (LLMs) with graph-structured data has become a pivotal and fast evolving research frontier, drawing strong interest from both academia and industry. The 2nd LLM+Graph Workshop, co-located with the 51st International Conference on Very Large Data Bases (VLDB 2025) in London, focused on advancing algorithms and systems that bridge LLMs, graph data management, and graph machine learning for practical applications. This report highlights the key research directions, challenges, and innovative solutions presented by the workshop's speakers.<\/jats:p>","DOI":"10.1145\/3829088.3829096","type":"journal-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T15:43:41Z","timestamp":1784648621000},"page":"58-64","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LLM+Graph@VLDB'2025 Workshop Summary"],"prefix":"10.1145","volume":"55","author":[{"given":"Yixiang","family":"Fang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arijit","family":"Khan","sequence":"additional","affiliation":[{"name":"Bowling Green State University,, Bowling Green, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianxing","family":"Wu","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Da","family":"Yan","sequence":"additional","affiliation":[{"name":"Indiana University Bloomington, Bloomington, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"SQLyzr: A comprehensive benchmark and framework for evaluating text-to-sql systems. Master\u2019s thesis","author":"Abedini S.","year":"2026","unstructured":"S. Abedini. SQLyzr: A comprehensive benchmark and framework for evaluating text-to-sql systems. Master\u2019s thesis, University of Waterloo, Apr. 2026. Advisor: M. Tamer \u00d6zsu. Available at https:\/\/hdl.handle.net\/10012\/23045."},{"key":"e_1_2_1_2_1","volume-title":"Proceedings of the VLDB Endowment. ISSN, 2150: 8097","author":"Akillioglu K.","unstructured":"K. Akillioglu, A. Chakraborty, S. Voruganti, and M. T. \u00d6zsu. Research challenges in relational database management systems for llm queries. Proceedings of the VLDB Endowment. ISSN, 2150:8097."},{"key":"e_1_2_1_3_1","first-page":"1","volume-title":"Proceedings of the 8th International Conference on Web Intelligence, Mining and Semantics","author":"Brati\u00b4c B.","year":"2018","unstructured":"B. Brati\u00b4c, M. E. Houle, V. Kurbalija, V. Oria, and M. Radovanovi\u00b4c. Nn-descent on high-dimensional data. In Proceedings of the 8th International Conference on Web Intelligence, Mining and Semantics, pages 1-8, 2018."},{"key":"e_1_2_1_4_1","volume-title":"Chat2Graph: A Graph Native Agentic System. https: \/\/github.com\/TuGraph-family\/chat2graph","year":"2025","unstructured":"Chat2Graph. Chat2Graph: A Graph Native Agentic System. https: \/\/github.com\/TuGraph-family\/chat2graph, 2025."},{"key":"e_1_2_1_5_1","volume-title":"Graphcompliance: Aligning policy and context graphs for llm-based regulatory compliance. arXiv preprint arXiv:2510.26309","author":"Chung J.","year":"2025","unstructured":"J. Chung, R. Ko, W. Yoo, M. Onizuka, S. Kim, T.-W. Kim, and W.-Y. Shin. Graphcompliance: Aligning policy and context graphs for llm-based regulatory compliance. arXiv preprint arXiv:2510.26309, 2025."},{"key":"e_1_2_1_6_1","volume-title":"Graphraft: Retrieval augmented fine-tuning for knowledge graphs on graph databases. arXiv preprint arXiv:2504.05478","author":"Clemedtson A.","year":"2025","unstructured":"A. Clemedtson and B. Shi. Graphraft: Retrieval augmented fine-tuning for knowledge graphs on graph databases. arXiv preprint arXiv:2504.05478, 2025."},{"key":"e_1_2_1_7_1","volume-title":"VLDB 2025 Workshop: LLM+Graph","author":"Colombo A.","year":"2025","unstructured":"A. Colombo and F. Cambria. Llm-assisted construction of the united states legislative graph. VLDB 2025 Workshop: LLM+Graph, 2025."},{"key":"e_1_2_1_8_1","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1145\/1963405.1963487","volume-title":"Proceedings of the 20th international conference on World wide web","author":"Dong W.","year":"2011","unstructured":"W. Dong, C. Moses, and K. Li. Efficient k-nearest neighbor graph construction for generic similarity measures. In Proceedings of the 20th international conference on World wide web, pages 577-586, 2011."},{"key":"e_1_2_1_9_1","volume-title":"Beyond quacking: Deep integration of language models and rag into duckdb. arXiv preprint arXiv:2504.01157","author":"Dorbani A.","year":"2025","unstructured":"A. Dorbani, S. Yasser, J. Lin, and A. Mhedhbi. Beyond quacking: Deep integration of language models and rag into duckdb. arXiv preprint arXiv:2504.01157, 2025."},{"key":"e_1_2_1_10_1","volume-title":"From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130","author":"Edge D.","year":"2024","unstructured":"D. Edge, H. Trinh, N. Cheng, J. Bradley, A. Chao, A. Mody, S. Truitt, D. Metropolitansky, R. O. Ness, and J. Larson. From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130, 2024."},{"key":"e_1_2_1_11_1","volume-title":"Proceedings of the VLDB Endowment. ISSN, 2150: 8097","author":"Fang Y.","unstructured":"Y. Fang, A. Khan, T. Wu, and D. Yan. Llm+ graph: 2 nd international workshop on data management opportunities in bringing llms with graph data. Proceedings of the VLDB Endowment. ISSN, 2150:8097."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4224"},{"key":"e_1_2_1_13_1","volume-title":"https:\/\/huggingface.co\/datasets\/neo4j\/ text2cypher-2025v1","year":"2025","unstructured":"HF\/Neo4j. Text2Cypher-2025v1. https:\/\/huggingface.co\/datasets\/neo4j\/ text2cypher-2025v1, 2025."},{"key":"e_1_2_1_14_1","volume-title":"https:\/\/huggingface.co\/neo4j\/models","author":"Models Cypher","year":"2025","unstructured":"HF\/Neo4j. Text2Cypher Models. https:\/\/huggingface.co\/neo4j\/models, 2025."},{"key":"e_1_2_1_15_1","volume-title":"VLDB 2025 Workshop: LLM+Graph","author":"Ji Q.","year":"2025","unstructured":"Q. Ji, P. Shen, H. Zhu, G. Qi, Y. Sheng, L. Wu, K. Xu, and Y. Meng. Llm-hype: A targeted evaluation framework for hypernym-hyponym identification in large language models. VLDB 2025 Workshop: LLM+Graph, 2025."},{"key":"e_1_2_1_16_1","volume-title":"\u00d6zsu. Interacsparql: An interactive system for sparql query refinement using natural language explanations. arXiv preprint arXiv:2511.02002","author":"Jian X.","year":"2025","unstructured":"X. Jian, Z. Dong, and M. T. \u00d6zsu. Interacsparql: An interactive system for sparql query refinement using natural language explanations. arXiv preprint arXiv:2511.02002, 2025."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3749116.3749132"},{"key":"e_1_2_1_18_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Khattab O.","year":"2024","unstructured":"O. Khattab, A. Singhvi, P. Maheshwari, Z. Zhang, K. Santhanam, S. Haq, A. Sharma, T. T. Joshi, H. Moazam, H. Miller, et al. Dspy: Compiling declarative language model calls into state-of-the-art pipelines. In The Twelfth International Conference on Learning Representations, 2024."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696630.3728543"},{"key":"e_1_2_1_20_1","first-page":"748","volume-title":"Proceedings 28th International Conference on Extending Database Technology, EDBT 2025","author":"Le H. T.","year":"2025","unstructured":"H. T. Le, A. Bonifati, and A. Mauri. Graph consistency rule mining with llms: an exploratory study. In Proceedings 28th International Conference on Extending Database Technology, EDBT 2025, Barcelona, Spain, March 25-28, 2025, pages 748-754, 2025."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.14778\/3554821.3554824"},{"key":"e_1_2_1_22_1","volume-title":"Dgp: A dual-granularity prompting framework for fraud detection with graph-enhanced llms. arXiv preprint arXiv:2507.21653","author":"Li Y.","year":"2025","unstructured":"Y. Li, J. Hu, B. Hooi, B. He, and C. Chen. Dgp: A dual-granularity prompting framework for fraud detection with graph-enhanced llms. arXiv preprint arXiv:2507.21653, 2025."},{"key":"e_1_2_1_23_1","volume-title":"Marscode agent: Ai-native automated bug fixing. arXiv preprint arXiv:2409.00899","author":"Liu Y.","year":"2024","unstructured":"Y. Liu, P. Gao, X. Wang, J. Liu, Y. Shi, Z. Zhang, and C. Peng. Marscode agent: Ai-native automated bug fixing. arXiv preprint arXiv:2409.00899, 2024."},{"key":"e_1_2_1_24_1","volume-title":"Knowledge graph-based retrieval-augmented generation for schema matching. CoRR, abs\/2501.08686","author":"Ma C.","year":"2025","unstructured":"C. Ma, S. Chakrabarti, A. Khan, and B. Moln\u00e1r. Knowledge graph-based retrieval-augmented generation for schema matching. CoRR, abs\/2501.08686, 2025."},{"key":"e_1_2_1_25_1","volume-title":"Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs","author":"Malkov Y. A.","year":"2018","unstructured":"Y. A. Malkov and D. A. Yashunin. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE transactions on pattern analysis and machine intelligence, 42(4):824-836, 2018."},{"key":"e_1_2_1_26_1","volume-title":"VLDB 2025 Workshop: LLM+Graph","author":"Mihindukulasooriya N.","year":"2025","unstructured":"N. Mihindukulasooriya, N. S. D\u2019Souza, F. Chowdhury, and H. Samulowitz. Automatic prompt optimization for knowledge graph construction: Insights from an empirical study. VLDB 2025 Workshop: LLM+Graph, 2025."},{"key":"e_1_2_1_27_1","volume-title":"https: \/\/github.com\/neo4j-contrib\/gds-agent","author":"Agent GDS","year":"2025","unstructured":"Neo4j. GDS Agent. https: \/\/github.com\/neo4j-contrib\/gds-agent, 2025."},{"key":"e_1_2_1_28_1","unstructured":"Neo4j Inc. Neo4j graphrag python: Modular tools for knowledge graph rag 2025. GitHub repository."},{"key":"e_1_2_1_29_1","volume-title":"Enhancing text2cypher with schema filtering. arXiv preprint arXiv:2505.05118","author":"Ozsoy M. G.","year":"2025","unstructured":"M. G. Ozsoy. Enhancing text2cypher with schema filtering. arXiv preprint arXiv:2505.05118, 2025."},{"key":"e_1_2_1_30_1","first-page":"100","volume-title":"COLING 2025","author":"Ozsoy M. G.","year":"2025","unstructured":"M. G. Ozsoy, L. Messallem, J. Besga, and G. Minneci. Text2cypher: Bridging natural language and graph databases. COLING 2025, page 100, 2025."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3709735"},{"key":"e_1_2_1_32_1","volume-title":"Transactions on Graph Data and Knowledge","author":"Pan J.","year":"2023","unstructured":"J. Pan, S. Razniewski, J.-C. Kalo, S. Singhania, J. Chen, S. Dietze, H. Jabeen, J. Omeliyanenko, W. Zhang, M. Lissandrini, et al. Large language models and knowledge graphs: Opportunities and challenges. Transactions on Graph Data and Knowledge, 2023."},{"key":"e_1_2_1_33_1","volume-title":"VLDB 2025 Workshop: LLM+Graph","author":"Publio G. C.","year":"2025","unstructured":"G. C. Publio and J. E. L. Gayo. xpshacl: Explainable shacl validation using retrieval-augmented generation and large language models. VLDB 2025 Workshop: LLM+Graph, 2025."},{"key":"e_1_2_1_34_1","volume-title":"VLDB 2025 Workshop: LLM+Graph","author":"Schneider N. R.","year":"2025","unstructured":"N. R. Schneider, K. O\u2019Sullivan, and H. Samet. Graph-enhanced large language models for spatial search. VLDB 2025 Workshop: LLM+Graph, 2025."},{"key":"e_1_2_1_35_1","volume-title":"Gds agent: A graph algorithmic reasoning agent. arXiv preprint arXiv:2508.20637","author":"Shi B.","year":"2025","unstructured":"B. Shi and I. Panagiotas. Gds agent: A graph algorithmic reasoning agent. arXiv preprint arXiv:2508.20637, 2025."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645428"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714952"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/255"},{"key":"e_1_2_1_39_1","first-page":"12586","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"39","author":"Sun L.","year":"2025","unstructured":"L. Sun, Z. Zhang, Z. Wang, Y. Wang, Q. Wan, H. Li, H. Peng, and P. S. Yu. Pioneer: Physics-informed riemannian graph ode for entropy-increasing dynamics. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 12586-12594, 2025."},{"key":"e_1_2_1_40_1","volume-title":"IJCAI","author":"Sun L.","year":"2025","unstructured":"L. Sun, S. Zhou, B. Fang, H. Zhang, J. Ye, Y. Ye, and P. S. Yu. Trace: Structural riemannian bridge matching for transferable source localization in information propagation. IJCAI, 2025."},{"key":"e_1_2_1_41_1","first-page":"1","volume-title":"Proceedings of the 8th Joint Workshop on Graph Data Management Experiences & Systems (GRADES) and Network Data Analytics (NDA)","author":"Terdalkar H.","year":"2025","unstructured":"H. Terdalkar, A. Bonifati, and A. Mauri. Graph repairs with large language models: An empirical study. In Proceedings of the 8th Joint Workshop on Graph Data Management Experiences & Systems (GRADES) and Network Data Analytics (NDA), pages 1-10, 2025."},{"issue":"3","key":"e_1_2_1_42_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3725325","article-title":"Mixed approach graph-based indexing for approximate nearest neighbor search","volume":"3","author":"Voruganti S.","year":"2025","unstructured":"S. Voruganti and M. T. \u00d6zsu. Mirage-anns: Mixed approach graph-based indexing for approximate nearest neighbor search. Proceedings of the ACM on Management of Data, 3(3):1-27, 2025.","journal-title":"Proceedings of the ACM on Management of Data"},{"key":"e_1_2_1_43_1","volume-title":"Archrag: Attributed community-based hierarchical retrieval-augmented generation. arXiv preprint arXiv:2502.09891","author":"Wang S.","year":"2025","unstructured":"S. Wang, Y. Fang, Y. Zhou, X. Liu, and Y. Ma. Archrag: Attributed community-based hierarchical retrieval-augmented generation. arXiv preprint arXiv:2502.09891, 2025."},{"key":"e_1_2_1_44_1","doi-asserted-by":"crossref","first-page":"9820","DOI":"10.18653\/v1\/2024.emnlp-main.548","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","author":"Zhang B.","year":"2024","unstructured":"B. Zhang and H. Soh. Extract, define, canonicalize: An llm-based framework for knowledge graph construction. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 9820-9836, 2024."},{"key":"e_1_2_1_45_1","volume-title":"VLDB 2025 Workshop: LLM+Graph","author":"Zhang F.","year":"2025","unstructured":"F. Zhang, Z. Huang, Y. Zhou, Q. Guo, W. Luo, and X. Zhou. Scalable graph-based retrieval-augmented generation via locality-sensitive hashing. VLDB 2025 Workshop: LLM+Graph, 2025."},{"key":"e_1_2_1_46_1","volume-title":"Llm-enhanced data management. arXiv preprint arXiv:2402.02643","author":"Zhou X.","year":"2024","unstructured":"X. Zhou, X. Zhao, and G. Li. Llm-enhanced data management. arXiv preprint arXiv:2402.02643, 2024."},{"key":"e_1_2_1_47_1","volume-title":"The eleventh international conference on learning representations","author":"Zhou Y.","year":"2022","unstructured":"Y. Zhou, A. I. Muresanu, Z. Han, K. Paster, S. Pitis, H. Chan, and J. Ba. Large language models are human-level prompt engineers. In The eleventh international conference on learning representations, 2022."},{"key":"e_1_2_1_48_1","unstructured":"Y. Zhou Y. Su Y. Sun T. Wang R. He Y. Zhang S. Liang X. Liu Y. Ma and Y. Fang. In"},{"key":"e_1_2_1_49_1","volume-title":"VLDB 2025 Workshop: LLM+Graph","author":"Zhou Y.","year":"2025","unstructured":"Y. Zhou and S. Wang. Towards the next generation of agent systems: From rag to agentic ai. VLDB 2025 Workshop: LLM+Graph, 2025."}],"container-title":["ACM SIGMOD Record"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3829088.3829096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T15:44:22Z","timestamp":1784648662000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3829088.3829096"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,20]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,7,20]]}},"alternative-id":["10.1145\/3829088.3829096"],"URL":"https:\/\/doi.org\/10.1145\/3829088.3829096","relation":{},"ISSN":["0163-5808"],"issn-type":[{"value":"0163-5808","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7,20]]},"assertion":[{"value":"2026-07-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}