{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:14:04Z","timestamp":1783696444235,"version":"3.55.0"},"reference-count":55,"publisher":"Elsevier BV","issue":"7","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Processing & Management"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.ipm.2026.104876","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T14:52:51Z","timestamp":1777560771000},"page":"104876","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Multimodal large language model-driven entity alignment via hierarchical interaction"],"prefix":"10.1016","volume":"63","author":[{"given":"Jie","family":"Peng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongfu","family":"Zha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxue","family":"Shan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ipm.2026.104876_b1","series-title":"Proceedings of the 35th international conference on machine learning","first-page":"531","article-title":"Mutual information neural estimation","volume":"vol. 80","author":"Belghazi","year":"2018"},{"key":"10.1016\/j.ipm.2026.104876_b2","series-title":"Advances in neural information processing systems 26: 27th annual conference on neural information processing systems 2013. proceedings of a meeting held December 5-8, 2013, lake tahoe, nevada, United states","first-page":"2787","article-title":"Translating embeddings for modeling multi-relational data","author":"Bordes","year":"2013"},{"key":"10.1016\/j.ipm.2026.104876_b3","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"3317","article-title":"MEAformer: Multi-modal entity alignment transformer for meta modality hybrid","author":"Chen","year":"2023"},{"key":"10.1016\/j.ipm.2026.104876_b4","series-title":"Proceedings of the 31st international conference on computational linguistics","first-page":"141","article-title":"Noise-powered multi-modal knowledge graph representation framework","author":"Chen","year":"2025"},{"key":"10.1016\/j.ipm.2026.104876_b5","series-title":"The semantic web \u2013 ISWC 2023","first-page":"121","article-title":"Rethinking uncertainly missing and ambiguous visual modality in multi-modal entity alignment","author":"Chen","year":"2023"},{"key":"10.1016\/j.ipm.2026.104876_b6","series-title":"Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"118","article-title":"Multi-modal siamese network for entity alignment","author":"Chen","year":"2022"},{"issue":"7","key":"10.1016\/j.ipm.2026.104876_b7","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1145\/3654674","article-title":"TOMGPT: reliable text-only training approach for cost-effective multi-modal large language model","volume":"18","author":"Chen","year":"2024","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"10.1016\/j.ipm.2026.104876_b8","series-title":"39th IEEE international conference on data engineering","first-page":"3453","article-title":"Tele-knowledge pre-training for fault analysis","author":"Chen","year":"2023"},{"key":"10.1016\/j.ipm.2026.104876_b9","series-title":"39th IEEE international conference on data engineering","first-page":"2988","article-title":"Construction and applications of billion-scale pre-trained multimodal business knowledge graph","author":"Deng","year":"2023"},{"key":"10.1016\/j.ipm.2026.104876_b10","series-title":"9th international conference on learning representations","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"issue":"2, Part A","key":"10.1016\/j.ipm.2026.104876_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104393","article-title":"Learning path recommendation based on forgetting factors and knowledge graph awareness","volume":"63","author":"Fan","year":"2025","journal-title":"Information Processing and Management"},{"key":"10.1016\/j.ipm.2026.104876_b12","doi-asserted-by":"crossref","first-page":"598","DOI":"10.1016\/j.neucom.2021.03.132","article-title":"Multi-modal entity alignment in hyperbolic space","volume":"461","author":"Guo","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.ipm.2026.104876_b13","series-title":"Proceedings of the 2021 conference on empirical methods in natural language processing","first-page":"9180","article-title":"Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis","author":"Han","year":"2021"},{"key":"10.1016\/j.ipm.2026.104876_b14","series-title":"Efficient multimodal learning from data-centric perspective","author":"He","year":"2024"},{"key":"10.1016\/j.ipm.2026.104876_b15","series-title":"Advances in neural information processing systems 38: annual conference on neural information processing systems 2024, neurIPS 2024, vancouver, BC, Canada, December 10 - 15, 2024","first-page":"1438","article-title":"Matryoshka query transformer for large vision-language models","author":"Hu","year":"2024"},{"key":"10.1016\/j.ipm.2026.104876_b16","series-title":"Leveraging intra-modal and inter-modal interaction for multi-modal entity alignment","author":"Hu","year":"2024"},{"key":"10.1016\/j.ipm.2026.104876_b17","series-title":"The tenth international conference on learning representations","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"10.1016\/j.ipm.2026.104876_b18","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"938","article-title":"Collm: A large language model for composed image retrieval","author":"Huynh","year":"2025"},{"key":"10.1016\/j.ipm.2026.104876_b19","series-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"10.1016\/j.ipm.2026.104876_b20","series-title":"2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, salt lake city, UT, USA, June 18-22, 2018","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","author":"Kendall","year":"2018"},{"key":"10.1016\/j.ipm.2026.104876_b21","series-title":"International conference on language resources and evaluation","doi-asserted-by":"crossref","DOI":"10.63317\/4vqtjrgga3dy","article-title":"Improving content recommendation: Knowledge graph-based semantic contrastive learning for diversity and cold-start users","author":"Kim","year":"2024"},{"key":"10.1016\/j.ipm.2026.104876_b22","series-title":"The thirteenth international conference on learning representations","first-page":"728","article-title":"NV-embed: Improved techniques for training LLMs as generalist embedding models","author":"Lee","year":"2025"},{"key":"10.1016\/j.ipm.2026.104876_b23","series-title":"Multimodal reasoning with multimodal knowledge graph","author":"Lee","year":"2024"},{"key":"10.1016\/j.ipm.2026.104876_b24","series-title":"Proceedings of the 47th international ACM SIGIR conference on research and development in information retrieval","first-page":"2629","article-title":"Sphere: Expressive and interpretable knowledge graph embedding for set retrieval","author":"Li","year":"2024"},{"key":"10.1016\/j.ipm.2026.104876_b25","series-title":"Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing, EMNLP-IJCNLP 2019, Hong kong, China, November 3-7, 2019","first-page":"2723","article-title":"Semi-supervised entity alignment via joint knowledge embedding model and cross-graph model","author":"Li","year":"2019"},{"key":"10.1016\/j.ipm.2026.104876_b26","series-title":"Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"1631","article-title":"SimDiff: Simple denoising probabilistic latent diffusion model for data augmentation on multi-modal knowledge graph","author":"Li","year":"2024"},{"key":"10.1016\/j.ipm.2026.104876_b27","series-title":"Proceedings of the ACM web conference 2023, WWW 2023, austin, TX, USA, 30 April 2023 - 4 May 2023","first-page":"2499","article-title":"Attribute-consistent knowledge graph representation learning for multi-modal entity alignment","author":"Li","year":"2023"},{"key":"10.1016\/j.ipm.2026.104876_b28","series-title":"Proceedings of the 29th international conference on computational linguistics","first-page":"2572","article-title":"Multi-modal contrastive representation learning for entity alignment","author":"Lin","year":"2022"},{"key":"10.1016\/j.ipm.2026.104876_b29","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"4257","article-title":"Visual pivoting for (unsupervised) entity alignment","volume":"vol. 35","author":"Liu","year":"2021"},{"key":"10.1016\/j.ipm.2026.104876_b30","series-title":"The semantic web: 16th international conference, ESWC 2019, portoro\u017e, Slovenia, June 2\u20136, 2019, proceedings","first-page":"459","article-title":"MMKG: Multi-modal knowledge graphs","author":"Liu","year":"2019"},{"key":"10.1016\/j.ipm.2026.104876_b31","series-title":"The thirteenth international conference on learning representations, ICLR 2025, Singapore, April 24-28, 2025","article-title":"Generative representational instruction tuning","author":"Muennighoff","year":"2025"},{"issue":"2","key":"10.1016\/j.ipm.2026.104876_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103971","article-title":"Concept-aware embedding for logical query reasoning over knowledge graphs","volume":"62","author":"Pan","year":"2025","journal-title":"Information Processing and Management"},{"issue":"5","key":"10.1016\/j.ipm.2026.104876_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2023.103472","article-title":"Variety-aware GAN and online learning augmented self-training model for knowledge graph entity alignment","volume":"60","author":"Qian","year":"2023","journal-title":"Information Processing and Management"},{"key":"10.1016\/j.ipm.2026.104876_b34","series-title":"Proceedings of the 38th international conference on machine learning, ICML 2021, 18-24 July 2021, virtual event","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.ipm.2026.104876_b35","series-title":"Proceedings of the ACM web conference 2024","first-page":"3464","article-title":"Representation learning with large language models for recommendation","author":"Ren","year":"2024"},{"key":"10.1016\/j.ipm.2026.104876_b36","series-title":"IEEE\/CVF conference on computer vision and pattern recognition, CVPR 2023, vancouver, BC, Canada, June 17-24, 2023","first-page":"15888","article-title":"Towards all-in-one pre-training via maximizing multi-modal mutual information","author":"Su","year":"2023"},{"key":"10.1016\/j.ipm.2026.104876_b37","series-title":"Proceedings of the 27th international joint conference on artificial intelligence","first-page":"4396","article-title":"Bootstrapping entity alignment with knowledge graph embedding","author":"Sun","year":"2018"},{"key":"10.1016\/j.ipm.2026.104876_b38","series-title":"Proceedings of the 2018 conference on empirical methods in natural language processing, Brussels, Belgium, October 31 - November 4, 2018","first-page":"349","article-title":"Cross-lingual knowledge graph alignment via graph convolutional networks","author":"Wang","year":"2018"},{"key":"10.1016\/j.ipm.2026.104876_b39","series-title":"2024 IEEE 40th international conference on data engineering","first-page":"3559","article-title":"Towards semantic consistency: Dirichlet energy driven robust multi-modal entity alignment","author":"Wang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104876_b40","series-title":"Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: long papers), ACL 2024, bangkok, thailand, August 11-16, 2024","first-page":"11897","article-title":"Improving text embeddings with large language models","author":"Wang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104876_b41","series-title":"Advances in neural information processing systems 36: annual conference on neural information processing systems 2023, neurIPS 2023, new orleans, la, USA, December 10 - 16, 2023","first-page":"478","article-title":"Achieving cross modal generalization with multimodal unified representation","author":"Xia","year":"2023"},{"issue":"6","key":"10.1016\/j.ipm.2026.104876_b42","doi-asserted-by":"crossref","DOI":"10.1007\/s11704-024-40555-y","article-title":"Large language models for generative information extraction: a survey","volume":"18","author":"Xu","year":"2024","journal-title":"Frontiers Comput. Sci."},{"key":"10.1016\/j.ipm.2026.104876_b43","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"3715","article-title":"Cross-modal graph attention network for entity alignment","author":"Xu","year":"2023"},{"issue":"8","key":"10.1016\/j.ipm.2026.104876_b44","doi-asserted-by":"crossref","first-page":"7554","DOI":"10.1109\/TCSVT.2025.3549953","article-title":"Avltrack: Dynamic sparse learning for aerial vision-language tracking","volume":"35","author":"Xue","year":"2025","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.ipm.2026.104876_b45","series-title":"Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval","first-page":"2486","article-title":"Biomedical information retrieval incorporating knowledge graph for explainable precision medicine","author":"Yang","year":"2020"},{"key":"10.1016\/j.ipm.2026.104876_b46","series-title":"Darec: A disentangled alignment framework for large language model and recommender system","author":"Yang","year":"2024"},{"issue":"6","key":"10.1016\/j.ipm.2026.104876_b47","doi-asserted-by":"crossref","first-page":"3312","DOI":"10.1109\/TKDE.2025.3548160","article-title":"Dual test-time training for out-of-distribution recommender system","volume":"37","author":"Yang","year":"2025","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.ipm.2026.104876_b48","series-title":"Qwen2 technical report","author":"Yang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104876_b49","series-title":"Qwen2.5 technical report","author":"Yang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104876_b50","series-title":"IEEE\/CVF international conference on computer vision, ICCV 2023, Paris, France, October 1-6, 2023","first-page":"11941","article-title":"Sigmoid loss for language image pre-training","author":"Zhai","year":"2023"},{"issue":"4","key":"10.1016\/j.ipm.2026.104876_b51","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104156","article-title":"MCCI: A multi-channel collaborative interaction framework for multimodal knowledge graph completion","volume":"62","author":"Zhang","year":"2025","journal-title":"Information Processing and Management"},{"issue":"3","key":"10.1016\/j.ipm.2026.104876_b52","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.104048","article-title":"Graph structure prefix injection transformer for multi-modal entity alignment","volume":"62","author":"Zhang","year":"2025","journal-title":"Information Processing and Management"},{"key":"10.1016\/j.ipm.2026.104876_b53","series-title":"Companion proceedings of the ACM on web conference 2024, WWW 2024, Singapore, Singapore, May 13-17, 2024","first-page":"170","article-title":"NoteLLM: A retrievable large language model for note recommendation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104876_b54","series-title":"Advances in neural information processing systems 36: annual conference on neural information processing systems 2023, neurIPS 2023, new orleans, la, USA, December 10 - 16, 2023","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","author":"Zheng","year":"2023"},{"key":"10.1016\/j.ipm.2026.104876_b55","series-title":"Proceedings of the twenty-sixth international joint conference on artificial intelligence, IJCAI 2017, melbourne, Australia, August 19-25, 2017","first-page":"4258","article-title":"Iterative entity alignment via joint knowledge embeddings","author":"Zhu","year":"2017"}],"container-title":["Information Processing & Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326002670?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326002670?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:33:40Z","timestamp":1783694020000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0306457326002670"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":55,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,11]]}},"alternative-id":["S0306457326002670"],"URL":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104876","relation":{},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multimodal large language model-driven entity alignment via hierarchical interaction","name":"articletitle","label":"Article Title"},{"value":"Information Processing & Management","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104876","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104876"}}