{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:00:31Z","timestamp":1765339231213,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3762048","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"13872-13873","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["The ACM Multimedia 2025 Grand Challenge of Truthful and Responsible Multimodal Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2298-3450","authenticated-orcid":false,"given":"Xudong","family":"Han","sequence":"first","affiliation":[{"name":"University of Sussex, Brighton and Hove, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5786-6489","authenticated-orcid":false,"given":"Kai","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1750-3375","authenticated-orcid":false,"given":"Yanlin","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1758-5936","authenticated-orcid":false,"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3846-9157","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, China"}]}],"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)."},{"volume-title":"Responsible AI","author":"Agarwal Sray","key":"e_1_3_2_1_2_1","unstructured":"Sray Agarwal and Shashin Mishra. 2021. Responsible AI. Springer."},{"key":"e_1_3_2_1_3_1","volume-title":"Hallucination of multimodal large language models: A survey. arXiv preprint arXiv:2404.18930","author":"Bai Zechen","year":"2024","unstructured":"Zechen Bai, Pichao Wang, Tianjun Xiao, Tong He, Zongbo Han, Zheng Zhang, and Mike Zheng Shou. 2024. Hallucination of multimodal large language models: A survey. arXiv preprint arXiv:2404.18930 (2024)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1108\/JEIM-06-2020-0233"},{"key":"e_1_3_2_1_5_1","volume-title":"Unified hallucination detection for multimodal large language models. arXiv preprint arXiv:2402.03190","author":"Chen Xiang","year":"2024","unstructured":"Xiang Chen, Chenxi Wang, Yida Xue, Ningyu Zhang, Xiaoyan Yang, Qiang Li, Yue Shen, Lei Liang, Jinjie Gu, and Huajun Chen. 2024. Unified hallucination detection for multimodal large language models. arXiv preprint arXiv:2402.03190 (2024)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689090.3689388"},{"key":"e_1_3_2_1_7_1","volume-title":"VITRON: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing.","author":"Fei Hao","year":"2024","unstructured":"Hao Fei, Shengqiong Wu, Hanwang Zhang, Tat-Seng Chua, and Shuicheng Yan. 2024b. VITRON: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing. (2024)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3393452"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3689171"},{"key":"e_1_3_2_1_10_1","volume-title":"Forty-second International Conference on Machine Learning.","author":"Fei Hao","year":"2025","unstructured":"Hao Fei, Yuan Zhou, Juncheng Li, Xiangtai Li, Qingshan Xu, Bobo Li, Shengqiong Wu, Yaoting Wang, Junbao Zhou, Jiahao Meng, et al., 2025. On path to multimodal generalist: General-level and general-bench. In Forty-second International Conference on Machine Learning."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00454"},{"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","doi-asserted-by":"publisher","DOI":"10.1080\/08913811.2013.843872"},{"key":"e_1_3_2_1_14_1","volume-title":"Fact-checking: A meta-analysis of what works and for whom. Political communication","author":"Walter Nathan","year":"2020","unstructured":"Nathan Walter, Jonathan Cohen, R Lance Holbert, and Yasmin Morag. 2020. Fact-checking: A meta-analysis of what works and for whom. Political communication, Vol. 37, 3 (2020), 350-375."},{"key":"e_1_3_2_1_15_1","volume-title":"Multimodal chain-of-thought reasoning: A comprehensive survey. arXiv preprint arXiv:2503.12605","author":"Wang Yaoting","year":"2025","unstructured":"Yaoting Wang, Shengqiong Wu, Yuecheng Zhang, Shuicheng Yan, Ziwei Liu, Jiebo Luo, and Hao Fei. 2025. Multimodal chain-of-thought reasoning: A comprehensive survey. arXiv preprint arXiv:2503.12605 (2025)."},{"key":"e_1_3_2_1_16_1","volume-title":"Towards Semantic Equivalence of Tokenization in Multimodal LLM. arXiv preprint arXiv:2406.05127","author":"Wu Shengqiong","year":"2024","unstructured":"Shengqiong Wu, Hao Fei, Xiangtai Li, Jiayi Ji, Hanwang Zhang, Tat-Seng Chua, and Shuicheng Yan. 2024a. Towards Semantic Equivalence of Tokenization in Multimodal LLM. arXiv preprint arXiv:2406.05127 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Shuicheng Yan, and Tat-Seng Chua.","author":"Wu Shengqiong","year":"2024","unstructured":"Shengqiong Wu, Hao Fei, Liangming Pan, William Yang Wang, Shuicheng Yan, and Tat-Seng Chua. 2024b. Combating Multimodal LLM Hallucination via Bottom-up Holistic Reasoning. arXiv preprint arXiv:2412.11124 (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Wu Shengqiong","year":"2024","unstructured":"Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, and Tat-Seng Chua. 2024c. NExT-GPT: Any-to-Any Multimodal LLM. In Proceedings of the International Conference on Machine Learning."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x"},{"key":"e_1_3_2_1_20_1","volume-title":"Less is more: Mitigating multimodal hallucination from an eos decision perspective. arXiv preprint arXiv:2402.14545","author":"Yue Zihao","year":"2024","unstructured":"Zihao Yue, Liang Zhang, and Qin Jin. 2024. Less is more: Mitigating multimodal hallucination from an eos decision perspective. arXiv preprint arXiv:2402.14545 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"Chen Change Loy, and Shuicheng Yan","author":"Zhang Tao","year":"2024","unstructured":"Tao Zhang, Xiangtai Li, Hao Fei, Haobo Yuan, Shengqiong Wu, Shunping Ji, Chen Change Loy, and Shuicheng Yan. 2024. Omg-llava: Bridging image-level, object-level, pixel-level reasoning and understanding. arXiv preprint arXiv:2406.19389 (2024)."}],"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\/3746027.3762048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T03:58:46Z","timestamp":1765339126000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3762048"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":21,"alternative-id":["10.1145\/3746027.3762048","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3762048","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"}}]}}