{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:23:50Z","timestamp":1787689430430,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["No. 62572097, No. 62176043, and No. U22A2097"],"award-info":[{"award-number":["No. 62572097, No. 62176043, and No. U22A2097"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780213","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"588-599","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["From Shallow Humor to Metaphor: Towards Label-Free Harmful Meme Detection via LMM Agent Self-Improvement"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0876-0497","authenticated-orcid":false,"given":"Jian","family":"Lang","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4977-1657","authenticated-orcid":false,"given":"Rongpei","family":"Hong","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8163-3146","authenticated-orcid":false,"given":"Ting","family":"Zhong","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2045-7369","authenticated-orcid":false,"given":"Leiting","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9621-5414","authenticated-orcid":false,"given":"Qiang","family":"Gao","sequence":"additional","affiliation":[{"name":"Southwestern University of Finance and Economics, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8038-8150","authenticated-orcid":false,"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China and Intelligent Digital Media Technology Key Laboratory of Sichuan Province, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Abdelrahman Abouelenin Atabak Ashfaq Adam Atkinson Hany Awadalla Nguyen Bach Jianmin Bao Alon Benhaim Martin Cai Vishrav Chaudhary et al. 2025. Phi-4-mini technical report: Compact yet powerful multimodal language models via mixture-of-loras. arXiv preprint arXiv:2503.01743 (2025)."},{"key":"e_1_3_2_2_2_1","unstructured":"Josh Abramson Arun Ahuja Federico Carnevale Petko Georgiev Alex Goldin Alden Hung Jessica Landon Jirka Lhotka Timothy Lillicrap Alistair Muldal et al. 2022. Improving multimodal interactive agents with reinforcement learning from human feedback. arXiv preprint arXiv:2211.11602 (2022)."},{"key":"e_1_3_2_2_3_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, 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, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_2_4_1","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","volume":"2204","author":"Alayrac Jean-Baptiste","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, A. Mensch, Katie Millican, Malcolm Reynolds, Roman Ring, Eliza Rutherford, Serkan Cabi, Tengda Han, Zhitao Gong, Sina Samangooei, Marianne Monteiro, Jacob Menick, Sebastian Borgeaud, Andy Brock, Aida Nematzadeh, Sahand Sharifzadeh, Mikolaj Binkowski, Ricardo Barreira, O. Vinyals, Andrew Zisserman, and K. Simonyan. 2022. Flamingo: a Visual Language Model for Few-Shot Learning. In Conference on Neural Information Processing Systems (NeurIPS), Vol. abs\/2204.14198."},{"key":"e_1_3_2_2_5_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612498"},{"key":"e_1_3_2_2_7_1","volume-title":"Prompting for Multimodal Hateful Meme Classification. In Conference on Empirical Methods in Natural Language Processing (EMNLP). 321-332","author":"Cao Rui","year":"2022","unstructured":"Rui Cao, Roy Ka-Wei Lee, Wen-Haw Chong, and Jing Jiang. 2022. Prompting for Multimodal Hateful Meme Classification. In Conference on Empirical Methods in Natural Language Processing (EMNLP). 321-332."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3648145"},{"key":"e_1_3_2_2_9_1","volume-title":"Robot shaping: Developing autonomous agents through learning. Artificial intelligence","author":"Dorigo Marco","year":"1994","unstructured":"Marco Dorigo and Marco Colombetti. 1994. Robot shaping: Developing autonomous agents through learning. Artificial intelligence, Vol. 71, 2 (1994), 321-370."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.semeval-1.74"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3689177"},{"key":"e_1_3_2_2_13_1","volume-title":"Bridging Modalities: Enhancing Cross-Modality Hate Speech Detection with Few-Shot In-Context Learning. In Conference on Empirical Methods in Natural Language Processing (EMNLP). 7785-7799","author":"Hee Ming Shan","year":"2024","unstructured":"Ming Shan Hee, Aditi Kumaresan, and Roy Ka-Wei Lee. 2024. Bridging Modalities: Enhancing Cross-Modality Hate Speech Detection with Few-Shot In-Context Learning. In Conference on Empirical Methods in Natural Language Processing (EMNLP). 7785-7799."},{"key":"e_1_3_2_2_14_1","volume-title":"Large Language Models Can Self-Improve. In Conference on Empirical Methods in Natural Language Processing (EMNLP). 1051-1068","author":"Huang Jiaxin","year":"2023","unstructured":"Jiaxin Huang, Shixiang Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, and Jiawei Han. 2023. Large Language Models Can Self-Improve. In Conference on Empirical Methods in Natural Language Processing (EMNLP). 1051-1068."},{"key":"e_1_3_2_2_15_1","volume-title":"Towards Low-Resource Harmful Meme Detection with LMM Agents. In Conference on Empirical Methods in Natural Language Processing (EMNLP).","author":"Huang Jianzhao","year":"2024","unstructured":"Jianzhao Huang, Hongzhan Lin, Liu Ziyan, Ziyang Luo, Guang Chen, and Jing Ma. 2024. Towards Low-Resource Harmful Meme Detection with LMM Agents. In Conference on Empirical Methods in Natural Language Processing (EMNLP)."},{"key":"e_1_3_2_2_16_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3587427"},{"key":"e_1_3_2_2_18_1","volume-title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes. In Conference on Neural Information Processing Systems (NeurIPS)","volume":"2005","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 Conference on Neural Information Processing Systems (NeurIPS), Vol. abs\/2005.04790."},{"key":"e_1_3_2_2_19_1","volume-title":"Biting Off More Than You Can Detect: Retrieval-Augmented Multimodal Experts for Short Video Hate Detection. In The Web Conference (WWW). ACM.","author":"Lang Jian","year":"2025","unstructured":"Jian Lang, Rongpei Hong, Jin Xu, Yili Li, Xovee Xu, and Fan Zhou. 2025. Biting Off More Than You Can Detect: Retrieval-Augmented Multimodal Experts for Short Video Hate Detection. In The Web Conference (WWW). ACM."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i2.19108"},{"key":"e_1_3_2_2_21_1","volume-title":"ACM International Conference on Multimedia (MM). 5138-5147","author":"Ka-Wei Lee Roy","year":"2021","unstructured":"Roy Ka-Wei Lee, Rui Cao, Ziqing Fan, Jing Jiang, and Wen-Haw Chong. 2021. Disentangling hate in online memes. In ACM International Conference on Multimedia (MM). 5138-5147."},{"key":"e_1_3_2_2_22_1","volume-title":"International Conference on Machine Learning (ICML). PMLR, 6028-6039","author":"Liang Jian","year":"2020","unstructured":"Jian Liang, Dapeng Hu, and Jiashi Feng. 2020. Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In International Conference on Machine Learning (ICML). PMLR, 6028-6039."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645381"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.611"},{"key":"e_1_3_2_2_25_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Liu Xiao","year":"2025","unstructured":"Xiao Liu, Tianjie Zhang, Yu Gu, Iat Long Iong, Yifan Xu, Xixuan Song, Shudan Zhang, Hanyu Lai, Xinyi Liu, Hanlin Zhao, et al., 2025. Visualagentbench: Towards large multimodal models as visual foundation agents. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_26_1","volume-title":"Towards Comprehensive Detection of Chinese Harmful Memes. In Conference on Neural Information Processing Systems (NeurIPS).","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 Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_2_27_1","volume-title":"Self-Refine: Iterative Refinement with Self-Feedback. In Conference on Neural Information Processing Systems (NeurIPS).","author":"Madaan Aman","year":"2023","unstructured":"Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Shashank Gupta, Bodhisattwa Prasad Majumder, Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, and Peter Clark. 2023. Self-Refine: Iterative Refinement with Self-Feedback. In Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350939"},{"key":"e_1_3_2_2_29_1","volume-title":"Detecting Harmful Memes and Their Targets. In Annual Meeting of the Association for Computational Linguistics (ACL). 2783-2796","author":"Pramanick Shraman","year":"2021","unstructured":"Shraman Pramanick, Dimitar Dimitrov, Rituparna Mukherjee, Shivam Sharma, Md. Shad Akhtar, Preslav Nakov, and Tanmoy Chakraborty. 2021a. Detecting Harmful Memes and Their Targets. In Annual Meeting of the Association for Computational Linguistics (ACL). 2783-2796."},{"key":"e_1_3_2_2_30_1","volume-title":"MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets. In Conference on Empirical Methods in Natural Language Processing (EMNLP). 4439-4455","author":"Pramanick Shraman","year":"2021","unstructured":"Shraman Pramanick, Shivam Sharma, Dimitar Dimitrov, Md. Shad Akhtar, Preslav Nakov, and Tanmoy Chakraborty. 2021b. MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets. In Conference on Empirical Methods in Natural Language Processing (EMNLP). 4439-4455."},{"key":"e_1_3_2_2_31_1","volume-title":"International Conference on Machine Learning (ICML). 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 (ICML). PMLR, 8748-8763."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3970"},{"key":"e_1_3_2_2_33_1","volume-title":"Michael G\u00fcnther, Bo Wang, Markus Krimmel, Feng Wang, Georgios Mastrapas, Andreas Koukounas, Nan Wang, et al.","author":"Sturua Saba","year":"2024","unstructured":"Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram, Michael G\u00fcnther, Bo Wang, Markus Krimmel, Feng Wang, Georgios Mastrapas, Andreas Koukounas, Nan Wang, et al., 2024. jina-embeddings-v3: Multilingual embeddings with task lora. arXiv preprint arXiv:2409.10173 (2024)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_1"},{"key":"e_1_3_2_2_35_1","first-page":"6561","article-title":"Learning Multimodal Contrast with Cross-modal Memory and Reinforced Contrast Recognition. In Findings of the Association for Computational Linguistics ACL","author":"Tian Yuanhe","year":"2024","unstructured":"Yuanhe Tian, Fei Xia, and Yan Song. 2024. Learning Multimodal Contrast with Cross-modal Memory and Reinforced Contrast Recognition. In Findings of the Association for Computational Linguistics ACL. Association for Computational Linguistics, 6561-6573.","journal-title":"Association for Computational Linguistics"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1849"},{"key":"e_1_3_2_2_37_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Wang Dequan","year":"2021","unstructured":"Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno A. Olshausen, and Trevor Darrell. 2021. Tent: Fully Test-Time Adaptation by Entropy Minimization. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_38_1","volume-title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In Conference on Neural Information Processing Systems (NeurIPS).","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 Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_2_39_1","volume-title":"HyperHatePrompt: A Hypergraph-based Prompting Fusion Model for Multimodal Hate Detection. In International Conference on Computational Linguistics (COLING).","author":"Xu Bo","year":"2025","unstructured":"Bo Xu, Erchen Yu, Jiahui Zhou, Hongfei Lin, and Linlin Zong. 2025. HyperHatePrompt: A Hypergraph-based Prompting Fusion Model for Multimodal Hate Detection. In International Conference on Computational Linguistics (COLING)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2971427"},{"key":"e_1_3_2_2_41_1","volume-title":"Invariant Meets Specific: A Scalable Harmful Memes Detection Framework. In ACM International Conference on Multimedia (MM). 4788-4797","author":"Yang Chuanpeng","year":"2023","unstructured":"Chuanpeng Yang, Fuqing Zhu, Jizhong Han, and Songlin Hu. 2023. Invariant Meets Specific: A Scalable Harmful Memes Detection Framework. In ACM International Conference on Multimedia (MM). 4788-4797."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"e_1_3_2_2_43_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al., 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_2_44_1","volume-title":"ExpeL: LLM Agents Are Experiential Learners. In AAAI Conference on Artificial Intelligence (AAAI). 19632-19642","author":"Zhao Andrew","year":"2024","unstructured":"Andrew Zhao, Daniel Huang, Quentin Xu, Matthieu Lin, Yong-Jin Liu, and Gao Huang. 2024. ExpeL: LLM Agents Are Experiential Learners. In AAAI Conference on Artificial Intelligence (AAAI). 19632-19642."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:07:57Z","timestamp":1787688477000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780213"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":44,"alternative-id":["10.1145\/3770854.3780213","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780213","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}