{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:45:55Z","timestamp":1780418755152,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730014","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:25:28Z","timestamp":1752456328000},"page":"559-569","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Is Having Rationales Enough? Rethinking Knowledge Enhancement for Multimodal Hateful Meme Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4094-2540","authenticated-orcid":false,"given":"Junyu","family":"Lu","sequence":"first","affiliation":[{"name":"Key Laboratory of Social Computing and Cognitive Intelligence, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-978X","authenticated-orcid":false,"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Social Computing and Cognitive Intelligence, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9755-2471","authenticated-orcid":false,"given":"Xiaokun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Data Intelligence Lab, Department of Computer Science, City University of HongKong, HongKong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6262-954X","authenticated-orcid":false,"given":"Haohao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4958-3241","authenticated-orcid":false,"given":"Kaichun","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5557-7515","authenticated-orcid":false,"given":"Liang","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Social Computing and Cognitive Intelligence, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0872-7688","authenticated-orcid":false,"given":"Hongfei","family":"Lin","sequence":"additional","affiliation":[{"name":"Key Laboratory of Social Computing and Cognitive Intelligence, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2022.FINDINGS-ACL.88"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612498"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.22"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Eric Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma Albert Webson Shixiang Shane Gu Zhuyun Dai Mirac Suzgun Xinyun Chen Aakanksha Chowdhery Sharan Narang Gaurav Mishra Adams Yu Vincent Y. Zhao Yanping Huang Andrew M. Dai Hongkun Yu Slav Petrov Ed H. Chi Jeff Dean Jacob Devlin Adam Roberts Denny Zhou Quoc V. Le and Jason Wei. 2022. Scaling Instruction-Finetuned Language Models. CoRR Vol. abs\/2210.11416 (2022). https:\/\/doi.org\/10.48550\/ARXIV.2210.11416 arXiv:2210.11416","DOI":"10.48550\/ARXIV.2210.11416"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/N19-1423"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.FINDINGS-ACL.212"},{"key":"e_1_3_2_1_7_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2022.ACL-LONG.390"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.semeval-1.74"},{"key":"e_1_3_2_1_10_1","volume-title":"Complexity-Based Prompting for Multi-step Reasoning. In The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Fu Yao","year":"2023","unstructured":"Yao Fu, Hao Peng, Ashish Sabharwal, Peter Clark, and Tushar Khot. 2023. Complexity-Based Prompting for Multi-step Reasoning. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/pdf?id=yf1icZHC-l9"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.FINDINGS-EMNLP.273"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the Eighth International Joint Conference on Natural Language Processing, IJCNLP 2017","volume":"39","author":"Ghader Hamidreza","year":"2017","unstructured":"Hamidreza Ghader and Christof Monz. 2017. What does Attention in Neural Machine Translation Pay Attention to?. In Proceedings of the Eighth International Joint Conference on Natural Language Processing, IJCNLP 2017, Taipei, Taiwan, November 27 - December 1, 2017 - Volume 1: Long Papers, Greg Kondrak and Taro Watanabe (Eds.). Asian Federation of Natural Language Processing, 30-39. https:\/\/aclanthology.org\/I17-1004\/"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093414"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2402.01680"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/665"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512260"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2311.05232"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3587427"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_2_1_21_1","first-page":"40","volume-title":"NeurIPS 2019 Workshop","author":"Kiela Douwe","year":"2019","unstructured":"Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, and Davide Testuggine. 2019. Supervised Multimodal Bitransformers for Classifying Images and Text. In Visually Grounded Interaction and Language (ViGIL), NeurIPS 2019 Workshop, Vancouver, Canada, December 13, 2019. https:\/\/vigilworkshop.github.io\/static\/papers\/40.pdf"},{"key":"e_1_3_2_1_22_1","volume-title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Kiela Douwe","year":"2020","unstructured":"Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, and Davide Testuggine. 2020. The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/1b84c4cee2b8b3d823b30e2d604b1878-Abstract.html"},{"key":"e_1_3_2_1_23_1","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large Language Models are Zero-Shot Reasoners. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/8bb0d291acd4acf06ef112099c16f326-Abstract-Conference.html"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592254"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475625"},{"key":"e_1_3_2_1_26_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning, ICML 2022","volume":"12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven C. H. Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 12888-12900. https:\/\/proceedings.mlr.press\/v162\/li22n.html"},{"key":"e_1_3_2_1_27_1","volume-title":"VisualBERT: A Simple and Performant Baseline for Vision and Language. CoRR","author":"Li Liunian Harold","year":"2019","unstructured":"Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019. VisualBERT: A Simple and Performant Baseline for Vision and Language. CoRR, Vol. abs\/1908.03557 (2019). arXiv:1908.03557 http:\/\/arxiv.org\/abs\/1908.03557"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645381"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.FINDINGS-EMNLP.611"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.01523"},{"key":"e_1_3_2_1_31_1","volume-title":"Visual Instruction Tuning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual Instruction Tuning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/6dcf277ea32ce3288914faf369fe6de0-Abstract-Conference.html"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/707"},{"key":"e_1_3_2_1_33_1","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9-Buc, Emily B. Fox, and Roman Garnett (Eds.). 13-23. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/c74d97b01eae257e44aa9d5bade97baf-Abstract.html"},{"key":"e_1_3_2_1_34_1","volume-title":"Towards Comprehensive Detection of Chinese Harmful Memes. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024","author":"Lu Junyu","year":"2024","unstructured":"Junyu Lu, Bo Xu, Xiaokun Zhang, Hongbo Wang, Haohao Zhu, Dongyu Zhang, Liang Yang, and Hongfei Lin. 2024. Towards Comprehensive Detection of Chinese Harmful Memes. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, Amir Globersons, Lester Mackey, Danielle Belgrave, Angela Fan, Ulrich Paquet, Jakub M. Tomczak, and Cheng Zhang (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2024\/hash\/17fc467c11997914127c001fdc801bea-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531925"},{"key":"e_1_3_2_1_36_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. CoRR Vol. abs\/2303.08774 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2303.08774 arXiv:2303.08774"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.246"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_40_1","volume-title":"A mathematical theory of communication. The Bell system technical journal","author":"Shannon Claude Elwood","year":"1948","unstructured":"Claude Elwood Shannon. 1948. A mathematical theory of communication. The Bell system technical journal, Vol. 27, 3 (1948), 379-423."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.118"},{"key":"e_1_3_2_1_42_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","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. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 5998-6008. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.FINDINGS-ACL.32"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/694"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-9443-0_8"},{"key":"e_1_3_2_1_46_1","volume-title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/9d5609613524ecf4f15af0f7b31abca4-Abstract-Conference.html"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.FINDINGS-EMNLP.167"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548255"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.FINDINGS-EMNLP.365"},{"key":"e_1_3_2_1_50_1","volume-title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language. In The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Zeng Andy","year":"2023","unstructured":"Andy Zeng, Maria Attarian, Brian Ichter, Krzysztof Marcin Choromanski, Adrian Wong, Stefan Welker, Federico Tombari, Aveek Purohit, Michael S. Ryoo, Vikas Sindhwani, Johnny Lee, Vincent Vanhoucke, and Pete Florence. 2023. Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=G2Q2Mh3avow"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V38I19.30178"},{"key":"e_1_3_2_1_52_1","article-title":"Multimodal Chain-of-Thought Reasoning in Language","volume":"2024","author":"Zhang Zhuosheng","year":"2024","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, and Alex Smola. 2024b. Multimodal Chain-of-Thought Reasoning in Language Models. Trans. Mach. Learn. Res., Vol. 2024 (2024). https:\/\/openreview.net\/forum?id=y1pPWFVfvR","journal-title":"Models. Trans. Mach. Learn. Res."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3501247.3531557"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:17:18Z","timestamp":1755865038000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730014"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":53,"alternative-id":["10.1145\/3726302.3730014","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730014","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}