{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:30:49Z","timestamp":1765308649680,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","funder":[{"name":"Shanghai University"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755044","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:50:47Z","timestamp":1761371447000},"page":"3310-3319","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4403-896X","authenticated-orcid":false,"given":"Ziyun","family":"Dai","sequence":"first","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7243-2783","authenticated-orcid":false,"given":"Xiaoqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9289-3827","authenticated-orcid":false,"given":"Shaohua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Business School, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4079-4725","authenticated-orcid":false,"given":"Yuanchen","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0754-5842","authenticated-orcid":false,"given":"Jide","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"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_2_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_3_1","volume-title":"Allava: Harnessing gpt4v-synthesized data for a lite vision-language model. arXiv preprint arXiv:2402.11684","author":"Chen Guiming Hardy","year":"2024","unstructured":"Guiming Hardy Chen, Shunian Chen, Ruifei Zhang, Junying Chen, Xiangbo Wu, Zhiyi Zhang, Zhihong Chen, Jianquan Li, Xiang Wan, and Benyou Wang. 2024a. Allava: Harnessing gpt4v-synthesized data for a lite vision-language model. arXiv preprint arXiv:2402.11684 (2024)."},{"key":"e_1_3_2_1_4_1","volume-title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478","author":"Chen Jun","year":"2023","unstructured":"Jun Chen, Deyao Zhu, Xiaoqian Shen, Xiang Li, Zechu Liu, Pengchuan Zhang, Raghuraman Krishnamoorthi, Vikas Chandra, Yunyang Xiong, and Mohamed Elhoseiny. 2023. MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478 (2023)."},{"key":"e_1_3_2_1_5_1","unstructured":"Zhe Chen Weiyun Wang Yue Cao Yangzhou Liu Zhangwei Gao Erfei Cui Jinguo Zhu Shenglong Ye Hao Tian Zhaoyang Liu et al. 2024b. Expanding performance boundaries of open-source multimodal models with model data and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. arXiv:2305.06500 [cs.CV] https:\/\/arxiv.org\/abs\/2305.06500"},{"key":"e_1_3_2_1_7_1","unstructured":"DeepSeek-AI. 2024. DeepSeek-V2: A Strong Economical and Efficient Mixture-of-Experts Language Model. arXiv:2405.04434 [cs.CL]"},{"key":"e_1_3_2_1_8_1","volume-title":"Composer: Creative and controllable image synthesis with composable conditions. arXiv preprint arXiv:2302.09778","author":"Huang Lianghua","year":"2023","unstructured":"Lianghua Huang, Di Chen, Yu Liu, Yujun Shen, Deli Zhao, and Jingren Zhou. 2023a. Composer: Creative and controllable image synthesis with composable conditions. arXiv preprint arXiv:2302.09778 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Visual hallucinations of multi-modal large language models. arXiv preprint arXiv:2402.14683","author":"Huang Wen","year":"2024","unstructured":"Wen Huang, Hongbin Liu, Minxin Guo, and Neil Zhenqiang Gong. 2024. Visual hallucinations of multi-modal large language models. arXiv preprint arXiv:2402.14683 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"Tag2Text: Guiding Vision-Language Model via Image Tagging. arXiv preprint arXiv:2303.05657","author":"Huang Xinyu","year":"2023","unstructured":"Xinyu Huang, Youcai Zhang, Jinyu Ma, Weiwei Tian, Rui Feng, Yuejie Zhang, Yaqian Li, Yandong Guo, and Lei Zhang. 2023b. Tag2Text: Guiding Vision-Language Model via Image Tagging. arXiv preprint arXiv:2303.05657 (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00106"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"e_1_3_2_1_13_1","volume-title":"arXiv:2304.02643","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Doll\u00e1r, and Ross Girshick. 2023. Segment Anything. arXiv:2304.02643 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023b. 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_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_8"},{"key":"e_1_3_2_1_16_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. 2023a. Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355 (2023)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"e_1_3_2_1_18_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. 2023b. 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_19_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li and Yong Jae Lee. 2023a. Improved Baselines with Visual Instruction Tuning."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_21_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024b. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_22_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. 2024c. A survey on hallucination in large vision-language models. arXiv preprint arXiv:2402.00253 (2024)."},{"key":"e_1_3_2_1_23_1","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Chunyuan Li Jianwei Yang Hang Su Jun Zhu et al. 2023c. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_2_1_25_1","unstructured":"OpenAI. 2022. Introducing ChatGPT. https:\/\/openai.com\/blog\/chatgpt"},{"key":"e_1_3_2_1_26_1","volume-title":"Daniel Coelho de Castro, and Ben Glocker","author":"Pawlowski Nick","year":"2020","unstructured":"Nick Pawlowski, Daniel Coelho de Castro, and Ben Glocker. 2020. Deep structural causal models for tractable counterfactual inference. Advances in neural information processing systems, Vol. 33 (2020), 857-869."},{"key":"e_1_3_2_1_27_1","volume-title":"Caiming Xiong, Silvio Savarese, et al.","author":"Qin Can","year":"2023","unstructured":"Can Qin, Shu Zhang, Ning Yu, Yihao Feng, Xinyi Yang, Yingbo Zhou, Huan Wang, Juan Carlos Niebles, Caiming Xiong, Silvio Savarese, et al., 2023. Unicontrol: A unified diffusion model for controllable visual generation in the wild. arXiv preprint arXiv:2305.11147 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Alleviating hallucination in large vision-language models with active retrieval augmentation. arXiv preprint arXiv:2408.00555","author":"Qu Xiaoye","year":"2024","unstructured":"Xiaoye Qu, Qiyuan Chen, Wei Wei, Jishuo Sun, and Jianfeng Dong. 2024. Alleviating hallucination in large vision-language models with active retrieval augmentation. arXiv preprint arXiv:2408.00555 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00673"},{"key":"e_1_3_2_1_30_1","unstructured":"Tianhe Ren Shilong Liu Ailing Zeng Jing Lin Kunchang Li He Cao Jiayu Chen Xinyu Huang Yukang Chen Feng Yan Zhaoyang Zeng Hao Zhang Feng Li Jie Yang Hongyang Li Qing Jiang and Lei Zhang. 2024. Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks. arXiv:2401.14159 [cs.CV]"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00547"},{"key":"e_1_3_2_1_32_1","unstructured":"Zhiqing Sun Sheng Shen Shengcao Cao Haotian Liu Chunyuan Li Yikang Shen Chuang Gan Liang-Yan Gui Yu-Xiong Wang Yiming Yang Kurt Keutzer and Trevor Darrell. 2023. Aligning Large Multimodal Models with Factually Augmented RLHF. (2023)."},{"key":"e_1_3_2_1_33_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_34_1","volume-title":"Boosting visual-language models by exploiting hard samples. arXiv preprint arXiv:2305.05208","author":"Wang Haonan","year":"2023","unstructured":"Haonan Wang, Minbin Huang, Runhui Huang, Lanqing Hong, Hang Xu, Tianyang Hu, Xiaodan Liang, Zhenguo Li, Hong Cheng, and Kenji Kawaguchi. 2023a. Boosting visual-language models by exploiting hard samples. arXiv preprint arXiv:2305.05208 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"To see is to believe: Prompting gpt-4v for better visual instruction tuning. arXiv preprint arXiv:2311.07574","author":"Wang Junke","year":"2023","unstructured":"Junke Wang, Lingchen Meng, Zejia Weng, Bo He, Zuxuan Wu, and Yu-Gang Jiang. 2023b. To see is to believe: Prompting gpt-4v for better visual instruction tuning. arXiv preprint arXiv:2311.07574 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53302-0_3"},{"key":"e_1_3_2_1_37_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_38_1","unstructured":"Yuan Yao Tianyu Yu Ao Zhang Chongyi Wang Junbo Cui Hongji Zhu Tianchi Cai Haoyu Li Weilin Zhao Zhihui He et al. 2024. MiniCPM-V: A GPT-4V Level MLLM on Your Phone. arXiv preprint arXiv:2408.01800 (2024)."},{"key":"e_1_3_2_1_39_1","unstructured":"Jiabo Ye Haiyang Xu Haowei Liu Anwen Hu Ming Yan Qi Qian Ji Zhang Fei Huang and Jingren Zhou. 2024. mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models. arXiv:2408.04840 [cs.CV] https:\/\/arxiv.org\/abs\/2408.04840"},{"key":"e_1_3_2_1_40_1","volume-title":"Evaluating Object Hallucination in Large Vision-Language Models. In The 2023 Conference on Empirical Methods in Natural Language Processing. https:\/\/openreview.net\/forum?id=xozJw0kZXF","author":"Jinpeng Wang Wayne Xin Kun Zhou","year":"2023","unstructured":"Kun Zhou Jinpeng Wang Wayne Xin Zhao Yifan Li, Yifan Du and Ji-Rong Wen. 2023. Evaluating Object Hallucination in Large Vision-Language Models. In The 2023 Conference on Empirical Methods in Natural Language Processing. https:\/\/openreview.net\/forum?id=xozJw0kZXF"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01230"},{"key":"e_1_3_2_1_42_1","volume-title":"Sung-Ho Bae, Seungkyu Lee, and Choong Seon Hong.","author":"Zhang Chaoning","year":"2023","unstructured":"Chaoning Zhang, Dongshen Han, Yu Qiao, Jung Uk Kim, Sung-Ho Bae, Seungkyu Lee, and Choong Seon Hong. 2023a. Faster segment anything: Towards lightweight sam for mobile applications. arXiv preprint arXiv:2306.14289 (2023)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_44_1","volume-title":"Beyond hallucinations: Enhancing lvlms through hallucination-aware direct preference optimization. arXiv preprint arXiv:2311.16839","author":"Zhao Zhiyuan","year":"2023","unstructured":"Zhiyuan Zhao, Bin Wang, Linke Ouyang, Xiaoyi Dong, Jiaqi Wang, and Conghui He. 2023. Beyond hallucinations: Enhancing lvlms through hallucination-aware direct preference optimization. arXiv preprint arXiv:2311.16839 (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"Analyzing and mitigating object hallucination in large vision-language models. arXiv preprint arXiv:2310.00754","author":"Zhou Yiyang","year":"2023","unstructured":"Yiyang Zhou, Chenhang Cui, Jaehong Yoon, Linjun Zhang, Zhun Deng, Chelsea Finn, Mohit Bansal, and Huaxiu Yao. 2023. Analyzing and mitigating object hallucination in large vision-language models. arXiv preprint arXiv:2310.00754 (2023)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755044","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:26:53Z","timestamp":1765308413000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755044"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":45,"alternative-id":["10.1145\/3746027.3755044","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755044","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"}}]}}