{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T20:49:37Z","timestamp":1776286177603,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China, National Natural Science Foundation of China","award":["No. 2023YFC3310700, No. 62172094"],"award-info":[{"award-number":["No. 2023YFC3310700, No. 62172094"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681467","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"9010-9018","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["AIGCs Confuse AI Too: Investigating and Explaining Synthetic Image-induced Hallucinations in Large Vision-Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4367-450X","authenticated-orcid":false,"given":"Yifei","family":"Gao","sequence":"first","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2301-3934","authenticated-orcid":false,"given":"Jiaqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1120-2447","authenticated-orcid":false,"given":"Zhiyu","family":"Lin","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0699-3205","authenticated-orcid":false,"given":"Jitao","family":"Sang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University & Peng Cheng Lab, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"A comprehensive survey of ai-generated content (aigc): A history of generative ai from gan to chatgpt. arXiv preprint arXiv:2303.04226","author":"Cao Yihan","year":"2023","unstructured":"Yihan Cao, Siyu Li, Yixin Liu, Zhiling Yan, Yutong Dai, Philip S Yu, and Lichao Sun. 2023. A comprehensive survey of ai-generated content (aigc): A history of generative ai from gan to chatgpt. arXiv preprint arXiv:2303.04226 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyond. arXiv preprint arXiv:2306.00419","author":"Chen Chuan","year":"2023","unstructured":"Chuan Chen, Zhenpeng Wu, Yanyi Lai, Wenlin Ou, Tianchi Liao, and Zibin Zheng. 2023. Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyond. arXiv preprint arXiv:2306.00419 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"e_1_3_2_1_6_1","volume-title":"Llms may dominate information access: Neural retrievers are biased towards llm-generated texts. arXiv preprint arXiv:2310.20501","author":"Dai Sunhao","year":"2023","unstructured":"Sunhao Dai, Yuqi Zhou, Liang Pang, Weihao Liu, Xiaolin Hu, Yong Liu, Xiao Zhang, and Jun Xu. 2023. Llms may dominate information access: Neural retrievers are biased towards llm-generated texts. arXiv preprint arXiv:2310.20501 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data. arXiv preprint arXiv:2306.09344","author":"Fu Stephanie","year":"2023","unstructured":"Stephanie Fu, Netanel Tamir, Shobhita Sundaram, Lucy Chai, Richard Zhang, Tali Dekel, and Phillip Isola. 2023. DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data. arXiv preprint arXiv:2306.09344 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnlssr.2023.08.001"},{"key":"e_1_3_2_1_9_1","volume-title":"Hallucination augmented contrastive learning for multimodal large language model. arXiv preprint arXiv:2312.06968","author":"Jiang Chaoya","year":"2023","unstructured":"Chaoya Jiang, Haiyang Xu, Mengfan Dong, Jiaxing Chen, Wei Ye, Ming Yan, Qinghao Ye, Ji Zhang, Fei Huang, and Shikun Zhang. 2023. Hallucination augmented contrastive learning for multimodal large language model. arXiv preprint arXiv:2312.06968 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Faithscore: Evaluating hallucinations in large vision-language models. arXiv preprint arXiv:2311.01477","author":"Jing Liqiang","year":"2023","unstructured":"Liqiang Jing, Ruosen Li, Yunmo Chen, Mengzhao Jia, and Xinya Du. 2023. Faithscore: Evaluating hallucinations in large vision-language models. arXiv preprint arXiv:2311.01477 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Mitigating object hallucinations in large vision-language models through visual contrastive decoding. arXiv preprint arXiv:2311.16922","author":"Leng Sicong","year":"2023","unstructured":"Sicong Leng, Hang Zhang, Guanzheng Chen, Xin Li, Shijian Lu, Chunyan Miao, and Lidong Bing. 2023. Mitigating object hallucinations in large vision-language models through visual contrastive decoding. arXiv preprint arXiv:2311.16922 (2023)."},{"key":"e_1_3_2_1_12_1","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. arxiv: 2301.12597 [cs.CV]"},{"key":"e_1_3_2_1_13_1","volume-title":"Wayne Xin Zhao, and Ji-Rong Wen","author":"Li Yifan","year":"2023","unstructured":"Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Liu Fuxiao","year":"2023","unstructured":"Fuxiao Liu, Kevin Lin, Linjie Li, Jianfeng Wang, Yaser Yacoob, and Lijuan Wang. 2023. Mitigating hallucination in large multi-modal models via robust instruction tuning. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","volume-title":"Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2023. Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)."},{"key":"e_1_3_2_1_16_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning."},{"key":"e_1_3_2_1_17_1","volume-title":"A survey on hallucination in large vision-language models. arXiv preprint arXiv:2402.00253","author":"Liu Hanchao","year":"2024","unstructured":"Hanchao Liu, Wenyuan Xue, Yifei Chen, Dapeng Chen, Xiutian Zhao, Ke Wang, Liping Hou, Rongjun Li, and Wei Peng. 2024. A survey on hallucination in large vision-language models. arXiv preprint arXiv:2402.00253 (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Seeing is not always believing: A Quantitative Study on Human Perception of AI-Generated Images. arXiv preprint arXiv:2304.13023","author":"Lu Zeyu","year":"2023","unstructured":"Zeyu Lu, Di Huang, Lei Bai, Xihui Liu, Jingjing Qu, and Wanli Ouyang. 2023. Seeing is not always believing: A Quantitative Study on Human Perception of AI-Generated Images. arXiv preprint arXiv:2304.13023 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Diversity and diffusion: Observations on synthetic image distributions with stable diffusion. arXiv preprint arXiv:2311.00056","author":"Marwood David","year":"2023","unstructured":"David Marwood, Shumeet Baluja, and Yair Alon. 2023. Diversity and diffusion: Observations on synthetic image distributions with stable diffusion. arXiv preprint arXiv:2311.00056 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_21_1","volume-title":"Beddhu Murali, and Andrew H Sung.","author":"Rana Md Shohel","year":"2022","unstructured":"Md Shohel Rana, Mohammad Nur Nobi, Beddhu Murali, and Andrew H Sung. 2022. Deepfake detection: A systematic literature review. IEEE access, Vol. 10 (2022), 25494--25513."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_23_1","volume-title":"An llm-free multi-dimensional benchmark for mllms hallucination evaluation. arXiv preprint arXiv:2311.07397","author":"Wang Junyang","year":"2023","unstructured":"Junyang Wang, Yuhang Wang, Guohai Xu, Jing Zhang, Yukai Gu, Haitao Jia, Ming Yan, Ji Zhang, and Jitao Sang. 2023. An llm-free multi-dimensional benchmark for mllms hallucination evaluation. arXiv preprint arXiv:2311.07397 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"Security and privacy on generative data in aigc: A survey. arXiv preprint arXiv:2309.09435","author":"Wang Tao","year":"2023","unstructured":"Tao Wang, Yushu Zhang, Shuren Qi, Ruoyu Zhao, Zhihua Xia, and Jian Weng. 2023. Security and privacy on generative data in aigc: A survey. arXiv preprint arXiv:2309.09435 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"Ai-generated content (aigc): A survey. arXiv preprint arXiv:2304.06632","author":"Wu Jiayang","year":"2023","unstructured":"Jiayang Wu, Wensheng Gan, Zefeng Chen, Shicheng Wan, and Hong Lin. 2023. Ai-generated content (aigc): A survey. arXiv preprint arXiv:2304.06632 (2023)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123618"},{"key":"e_1_3_2_1_27_1","volume-title":"AI-Generated Images Introduce Invisible Relevance Bias to Text-Image Retrieval. arXiv preprint arXiv:2311.14084","author":"Xu Shicheng","year":"2023","unstructured":"Shicheng Xu, Danyang Hou, Liang Pang, Jingcheng Deng, Jun Xu, Huawei Shen, and Xueqi Cheng. 2023. AI-Generated Images Introduce Invisible Relevance Bias to Text-Image Retrieval. arXiv preprint arXiv:2311.14084 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"AI-Generated Images as Data Source: The Dawn of Synthetic Era. arXiv preprint arXiv:2310.01830","author":"Yang Zuhao","year":"2023","unstructured":"Zuhao Yang, Fangneng Zhan, Kunhao Liu, Muyu Xu, and Shijian Lu. 2023. AI-Generated Images as Data Source: The Dawn of Synthetic Era. arXiv preprint arXiv:2310.01830 (2023)."},{"key":"e_1_3_2_1_29_1","unstructured":"Qinghao Ye Haiyang Xu Guohai Xu Jiabo Ye Ming Yan Yiyang Zhou Junyang Wang Anwen Hu Pengcheng Shi Yaya Shi et al. 2023. mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Text-to-image diffusion model in generative ai: A survey. arXiv preprint arXiv:2303.07909","author":"Zhang Chenshuang","year":"2023","unstructured":"Chenshuang Zhang, Chaoning Zhang, Mengchun Zhang, and In So Kweon. 2023. Text-to-image diffusion model in generative ai: A survey. arXiv preprint arXiv:2303.07909 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V","author":"Zhao Ganning","unstructured":"Ganning Zhao, Tingwei Shen, Suya You, and C-C Jay Kuo. 2023. Unsupervised synthetic image refinement via contrastive learning and consistent semantic-structural constraints. In Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V, Vol. 12538. SPIE, 440--449."},{"key":"e_1_3_2_1_32_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"if grounded. arXiv preprint arXiv:2401.01614","author":"Zheng Boyuan","year":"2024","unstructured":"Boyuan Zheng, Boyu Gou, Jihyung Kil, Huan Sun, and Yu Su. 2024. Gpt-4v (ision) is a generalist web agent, if grounded. arXiv preprint arXiv:2401.01614 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zou Xueyan","year":"2024","unstructured":"Xueyan Zou, Jianwei Yang, Hao Zhang, Feng Li, Linjie Li, Jianfeng Wang, Lijuan Wang, Jianfeng Gao, and Yong Jae Lee. 2024. Segment everything everywhere all at once. Advances in Neural Information Processing Systems, Vol. 36 (2024)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681467","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:47Z","timestamp":1750294667000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681467"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":34,"alternative-id":["10.1145\/3664647.3681467","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681467","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}