{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:21:52Z","timestamp":1784737312685,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754591","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:50:47Z","timestamp":1761371447000},"page":"2486-2495","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Entity Graph Alignment and Visual Reasoning for Multimodal Fake News Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5673-6735","authenticated-orcid":false,"given":"Guoyi","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2092-2059","authenticated-orcid":false,"given":"Die","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7195-0765","authenticated-orcid":false,"given":"Xiaomeng","family":"Fu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3184-4662","authenticated-orcid":false,"given":"Qirui","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0801-8443","authenticated-orcid":false,"given":"Yulei","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Bristol, Bristol, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7702-4290","authenticated-orcid":false,"given":"Xiaodan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9637-0587","authenticated-orcid":false,"given":"Honglei","family":"Lyu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-017-0143-x"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219861"},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on machine learning. PMLR, 1597-1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597-1607."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511968"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.37"},{"key":"e_1_3_2_1_6_1","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna. lmsys.org (accessed","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E Gonzalez, et al. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna. lmsys.org (accessed 14 April 2023) 2, 3 (2023), 6."},{"key":"e_1_3_2_1_7_1","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research 24, 240 (2023), 1-113.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.156"},{"key":"e_1_3_2_1_9_1","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171-4186."},{"key":"e_1_3_2_1_10_1","first-page":"4758","article-title":"A Generalized Deep Markov Random Fields Framework for Fake News Detection","author":"Dong Yiqi","year":"2023","unstructured":"Yiqi Dong, Dongxiao He, Xiaobao Wang, Yawen Li, Xiaowen Su, and Di Jin 0001. 2023. A Generalized Deep Markov Random Fields Framework for Fake News Detection.. In IJCAI. 4758-4765.","journal-title":"IJCAI."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.133"},{"key":"e_1_3_2_1_12_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems 27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01362"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i20.30214"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110125"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"e_1_3_2_1_18_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123454"},{"key":"e_1_3_2_1_20_1","volume-title":"Manish Gupta, and Vasudeva Varma.","author":"Khattar Dhruv","year":"2019","unstructured":"Dhruv Khattar, Jaipal Singh Goud, Manish Gupta, and Vasudeva Varma. 2019. Mvae: Multimodal variational autoencoder for fake news detection. In The world wide web conference. 2915-2921."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3595916.3626397"},{"key":"e_1_3_2_1_23_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3098988"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_27_1","volume-title":"Llavanext: Improved reasoning, ocr, and world knowledge.","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. 2024. Llavanext: Improved reasoning, ocr, and world knowledge."},{"key":"e_1_3_2_1_28_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems 36","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems 36 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-demo.1"},{"key":"e_1_3_2_1_30_1","volume-title":"Huaibo Huang, Zekun Li, Xing Cui, Weihong Deng, Zhaofeng He, et al. [n.d.]. FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs. In ACM Multimedia","author":"Liu Xuannan","year":"2024","unstructured":"Xuannan Liu, Pei Pei Li, Huaibo Huang, Zekun Li, Xing Cui, Weihong Deng, Zhaofeng He, et al. [n.d.]. FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs. In ACM Multimedia 2024."},{"key":"e_1_3_2_1_31_1","volume-title":"MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=D6zn6ozJs7","author":"Liu Xuannan","year":"2025","unstructured":"Xuannan Liu, Zekun Li, Pei Pei Li, Huaibo Huang, Shuhan Xia, Xing Cui, Linzhi Huang, Weihong Deng, and Zhaofeng He. 2025. MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=D6zn6ozJs7"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.316"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"e_1_3_2_1_36_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.386"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Gabriel Peyr\u00e9 Marco Cuturi et al. 2019. Computational optimal transport: With applications to data science. Foundations and Trends\u00ae in Machine Learning 11 5-6 (2019) 355-607.","DOI":"10.1561\/2200000073"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3481548"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01240"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462871"},{"key":"e_1_3_2_1_42_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and AndrewZisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511999"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681317"},{"key":"e_1_3_2_1_46_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_47_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_48_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583868"},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of the 31st ACM International Conference on Multimedia. 5696-5704","author":"Zhang Chuang","year":"2023","unstructured":"LongzhengWang, Chuang Zhang, Hongbo Xu, Yongxiu Xu, Xiaohan Xu, and Siqi Wang. 2023. Cross-modal contrastive learning for multimodal fake news detection. In Proceedings of the 31st ACM International Conference on Multimedia. 5696-5704."},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 2726-2736","author":"Wu Jiaying","year":"2023","unstructured":"Jiaying Wu, Shen Li, Ailin Deng, Miao Xiong, and Bryan Hooi. 2023. Promptand- align: prompt-based social alignment for few-shot fake news detection. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 2726-2736."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.347"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25670"},{"key":"e_1_3_2_1_55_1","volume-title":"Graph contrastive learning with augmentations. Advances in neural information processing systems 33","author":"You Yuning","year":"2020","unstructured":"Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, and Yang Shen. 2020. Graph contrastive learning with augmentations. Advances in neural information processing systems 33 (2020), 5812-5823."},{"key":"e_1_3_2_1_56_1","first-page":"3901","article-title":"A Convolutional Approach for Misinformation Identification","author":"Yu Feng","year":"2017","unstructured":"Feng Yu, Qiang Liu, ShuWu, LiangWang, Tieniu Tan, et al. 2017. A Convolutional Approach for Misinformation Identification.. In IJCAI. 3901-3907.","journal-title":"IJCAI."},{"key":"e_1_3_2_1_57_1","volume-title":"CoCa: Contrastive Captioners are Image-Text Foundation Models. Transactions on Machine Learning Research","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, ZiruiWang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022. CoCa: Contrastive Captioners are Image-Text Foundation Models. Transactions on Machine Learning Research (2022). https:\/\/openreview.net\/forum?id=Ee277P3AYC"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.313"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29618"},{"key":"e_1_3_2_1_60_1","first-page":"2542","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24","author":"Zhang Qiang","year":"2024","unstructured":"Qiang Zhang, Jiawei Liu, Fanrui Zhang, Jingyi Xie, and Zheng-Jun Zha. 2024. Natural language-centered inference network for multi-modal fake news detection. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24. 2542-2550."},{"key":"e_1_3_2_1_61_1","volume-title":"GS2F: Multimodal Fake News Detection Utilizing Graph Structure and Guided Semantic Fusion. ACM Transactions on Asian and Low-Resource Language Information Processing","author":"Zhou Dong","year":"2024","unstructured":"Dong Zhou, Qiang Ouyang, Nankai Lin, Yongmei Zhou, and Aimin Yang. 2024. GS2F: Multimodal Fake News Detection Utilizing Graph Structure and Guided Semantic Fusion. ACM Transactions on Asian and Low-Resource Language Information Processing (2024)."},{"key":"e_1_3_2_1_62_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=1tZbq88f27","author":"Zhu Deyao","year":"2024","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2024. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=1tZbq88f27"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:27:30Z","timestamp":1765308450000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754591"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":63,"alternative-id":["10.1145\/3746027.3754591","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754591","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}