{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:45:34Z","timestamp":1765309534497,"version":"3.46.0"},"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\/3746027.3754836","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"62-71","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Zero-Shot Multimodal Fact-Checking with Conceptual Reasoning"],"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":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1942-2074","authenticated-orcid":false,"given":"Haozhe","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"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","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-023-01028-5"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.828"},{"key":"e_1_3_2_1_4_1","volume-title":"Casper Hansen, Christian Hansen, and Jakob Grue Simonsen.","author":"Augenstein Isabelle","year":"2019","unstructured":"Isabelle Augenstein, Christina Lioma, Dongsheng Wang, Lucas Chaves Lima, Casper Hansen, Christian Hansen, and Jakob Grue Simonsen. 2019. MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims. In EMNLP. Association for Computational Linguistics."},{"key":"e_1_3_2_1_5_1","volume-title":"Perceptual symbol systems. The Behavioral and brain sciences\/Cambridge University Press","author":"Barsalou LW","year":"1999","unstructured":"LW Barsalou. 1999. Perceptual symbol systems. The Behavioral and brain sciences\/Cambridge University Press (1999)."},{"key":"e_1_3_2_1_6_1","volume-title":"A theory of learning from different domains. Machine learning","author":"Ben-David Shai","year":"2010","unstructured":"Shai Ben-David, John Blitzer, Koby Crammer, Alex Kulesza, Fernando Pereira, and Jennifer Wortman Vaughan. 2010. A theory of learning from different domains. Machine learning, Vol. 79 (2010), 151-175."},{"key":"e_1_3_2_1_7_1","volume-title":"One billion word benchmark for measuring progress in statistical language modeling. arXiv preprint arXiv:1312.3005","author":"Chelba Ciprian","year":"2013","unstructured":"Ciprian Chelba, Tomas Mikolov, Mike Schuster, Qi Ge, Thorsten Brants, Phillipp Koehn, and Tony Robinson. 2013. One billion word benchmark for measuring progress in statistical language modeling. arXiv preprint arXiv:1312.3005 (2013)."},{"key":"e_1_3_2_1_8_1","volume-title":"Detection, Intervention, and Open Issues.","author":"Chen C","year":"2022","unstructured":"C Chen, H Wang, M Shapiro, Y Xiao, F Wang, and K Shu. 2022. Combating Health Misinformation in Social Media: Characterization, Detection, Intervention, and Open Issues. (2022)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.474"},{"key":"e_1_3_2_1_10_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. 2023a. 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_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.156"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"e_1_3_2_1_13_1","unstructured":"Jie Gao Hella-Franziska Hoffmann Stylianos Oikonomou David Kiskovski and Anil Bandhakavi. 2022. Logically at Factify 2022: Multimodal Fact Verification. arXiv:2112.09253 [cs.CV] https:\/\/arxiv.org\/abs\/2112.09253"},{"key":"e_1_3_2_1_14_1","first-page":"179","volume-title":"55th Annual Meeting of the Association for Computational Linguistics, ACL","author":"Gardent Claire","year":"2017","unstructured":"Claire Gardent, Anastasia Shimorina, Shashi Narayan, and Laura Perez-Beltrachini. 2017. Creating training corpora for nlg micro-planning. In 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017. Association for Computational Linguistics (ACL), 179-188."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00454"},{"key":"e_1_3_2_1_16_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=sE7-XhLxHA","author":"He Pengcheng","year":"2023","unstructured":"Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2023. DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=sE7-XhLxHA"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.681"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.246"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"e_1_3_2_1_20_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_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.124"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.623"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_25_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. 2024c. Llavanext: Improved reasoning, ocr, and world knowledge."},{"key":"e_1_3_2_1_26_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. 2024d. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.fever-1.14"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.deeplo-1.18"},{"key":"e_1_3_2_1_29_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_30_1","volume-title":"European Conference on Computer Vision. 216-233","author":"Liu Yuan","year":"2024","unstructured":"Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, et al., 2024a. MMBench: Is Your Multi-modal Model an All-Around Player?. In European Conference on Computer Vision. 216-233."},{"key":"e_1_3_2_1_31_1","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume":"35","author":"Lu Pan","year":"2022","unstructured":"Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. 2022. Learn to explain: Multimodal reasoning via thought chains for science question answering. Advances in Neural Information Processing Systems, Vol. 35 (2022), 2507-2521.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v16i1.19323"},{"key":"e_1_3_2_1_33_1","volume-title":"FACTIFY: A Multi-Modal Fact Verification Dataset. In DE-FACTIFY@ AAAI.","author":"Mishra Shreyash","year":"2022","unstructured":"Shreyash Mishra, S Suryavardan, Amrit Bhaskar, Parul Chopra, Aishwarya N Reganti, Parth Patwa, Amitava Das, Tanmoy Chakraborty, Amit P Sheth, Asif Ekbal, et al., 2022. FACTIFY: A Multi-Modal Fact Verification Dataset. In DE-FACTIFY@ AAAI."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference. 6149-6157","author":"Nakamura Kai","year":"2020","unstructured":"Kai Nakamura, Sharon Levy, and William Yang Wang. 2020. Fakeddit: A New Multimodal Benchmark Dataset for Fine-grained Fake News Detection. In Proceedings of the Twelfth Language Resources and Evaluation Conference. 6149-6157."},{"key":"e_1_3_2_1_35_1","volume-title":"European Conference on Information Retrieval. 639-649","author":"Nakov Preslav","year":"2021","unstructured":"Preslav Nakov, Giovanni Da San Martino, Tamer Elsayed, Alberto Barr\u00f3n-Cede no, Rub\u00e9n M\u00edguez, Shaden Shaar, Firoj Alam, Fatima Haouari, Maram Hasanain, Nikolay Babulkov, et al., 2021. The CLEF-2021 CheckThat! Lab on Detecting Check-Worthy Claims, Previously Fact-Checked Claims, and Fake News. In European Conference on Information Retrieval. 639-649."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.441"},{"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":"publisher","DOI":"10.1109\/CVPR52733.2024.01240"},{"key":"e_1_3_2_1_39_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_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/1860625.1860629"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3549555.3549557"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_43_1","volume-title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models. arXiv:2503.16419 [cs.CL] https:\/\/arxiv.org\/abs\/2503.16419","author":"Sui Yang","year":"2025","unstructured":"Yang Sui, Yu-Neng Chuang, Guanchu Wang, Jiamu Zhang, Tianyi Zhang, Jiayi Yuan, Hongyi Liu, Andrew Wen, Shaochen Zhong, Hanjie Chen, and Xia Hu. 2025. Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models. arXiv:2503.16419 [cs.CL] https:\/\/arxiv.org\/abs\/2503.16419"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592230"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679826"},{"key":"e_1_3_2_1_46_1","volume-title":"Multimodal Geolocation Estimation of News Photos. In European Conference on Information Retrieval. 204-220","author":"Tahmasebzadeh Golsa","year":"2023","unstructured":"Golsa Tahmasebzadeh, Sherzod Hakimov, Ralph Ewerth, and Eric M\u00fcller-Budack. 2023. Multimodal Geolocation Estimation of News Photos. In European Conference on Information Retrieval. 204-220."},{"key":"e_1_3_2_1_47_1","volume-title":"FEVER: a large-scale dataset for fact extraction and VERification. arXiv preprint arXiv:1803.05355","author":"Thorne James","year":"2018","unstructured":"James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and VERification. arXiv preprint arXiv:1803.05355 (2018)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.448"},{"key":"e_1_3_2_1_49_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_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.387"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331248"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2067"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.519"},{"key":"e_1_3_2_1_55_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591879"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.556"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1047"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01337"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645455"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612183"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512264"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1216"}],"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\/3746027.3754836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:41:10Z","timestamp":1765309270000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754836"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":63,"alternative-id":["10.1145\/3746027.3754836","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754836","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"}}]}}