{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:01:12Z","timestamp":1783530072759,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589334.3645381","type":"proceedings-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T07:08:13Z","timestamp":1715152093000},"page":"2359-2370","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":48,"title":["Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4111-8334","authenticated-orcid":false,"given":"Hongzhan","family":"Lin","sequence":"first","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6037-0471","authenticated-orcid":false,"given":"Ziyang","family":"Luo","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2028-2407","authenticated-orcid":false,"given":"Wei","family":"Gao","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7464-8331","authenticated-orcid":false,"given":"Jing","family":"Ma","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7158-7046","authenticated-orcid":false,"given":"Bo","family":"Wang","sequence":"additional","affiliation":[{"name":"Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3749-3622","authenticated-orcid":false,"given":"Ruichao","family":"Yang","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Yejin Bang Samuel Cahyawijaya Nayeon Lee Wenliang Dai Dan Su Bryan Wilie Holy Lovenia Ziwei Ji Tiezheng Yu Willy Chung et al. 2023. A multitask multilingual multimodal evaluation of chatgpt on reasoning hallucination and interactivity. arXiv preprint arXiv:2302.04023 (2023).","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"e_1_3_2_2_2_1","volume-title":"Dialectical thinking","author":"Basseches Michael","year":"1984","unstructured":"Michael Basseches. 1984. Dialectical thinking. Norwood, NJ: Ablex (1984)."},{"key":"e_1_3_2_2_3_1","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems. 1877--1901","author":"Brown Tom B","year":"2020","unstructured":"Tom B Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. In Proceedings of the 34th International Conference on Neural Information Processing Systems. 1877--1901."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612498"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.22"},{"key":"e_1_3_2_2_6_1","volume-title":"Charles Sutton, Sebastian Gehrmann, et al.","author":"Chowdhery Aakanksha","year":"2022","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2022. Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022)."},{"key":"e_1_3_2_2_7_1","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Eric Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma et al. 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)."},{"key":"e_1_3_2_2_8_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Albert Li, Pascale Fung, and Steven C. H. Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Albert Li, Pascale Fung, and Steven C. H. Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. ArXiv (2023)."},{"key":"e_1_3_2_2_9_1","volume-title":"Japsimar Singh Wahi, and Siyao Li","author":"Das Abhishek","year":"2020","unstructured":"Abhishek Das, Japsimar Singh Wahi, and Siyao Li. 2020. Detecting hate speech in multi-modal memes. arXiv preprint arXiv:2012.14891 (2020)."},{"key":"e_1_3_2_2_10_1","volume-title":"Proceedings of NAACL-HLT. 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00373"},{"key":"e_1_3_2_2_12_1","volume-title":"Complexity-Based Prompting for Multi-step Reasoning. In The Eleventh International Conference on Learning Representations.","author":"Fu Yao","year":"2022","unstructured":"Yao Fu, Hao Peng, Ashish Sabharwal, Peter Clark, and Tushar Khot. 2022. Complexity-Based Prompting for Multi-step Reasoning. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_14_1","volume-title":"Decoding the Underlying Meaning of Multimodal Hateful Memes. arXiv preprint arXiv:2305.17678","author":"Hee Ming Shan","year":"2023","unstructured":"Ming Shan Hee, Wen-Haw Chong, and Roy Ka-Wei Lee. 2023. Decoding the Underlying Meaning of Multimodal Hateful Memes. arXiv preprint arXiv:2305.17678 (2023)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512260"},{"key":"e_1_3_2_2_16_1","volume-title":"Bad Actor","author":"Hu Beizhe","year":"2023","unstructured":"Beizhe Hu, Qiang Sheng, Juan Cao, Yuhui Shi, Yang Li, Danding Wang, and Peng Qi. 2023. Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection. arXiv preprint arXiv:2309.12247 (2023)."},{"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","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_2_2_19_1","volume-title":"Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950","author":"Kiela Douwe","year":"2019","unstructured":"Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, Ethan Perez, and Davide Testuggine. 2019. Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950 (2019)."},{"key":"e_1_3_2_2_20_1","unstructured":"Douwe Kiela Hamed Firooz Aravind Mohan Vedanuj Goswami Amanpreet Singh Casey A Fitzpatrick Peter Bull Greg Lipstein Tony Nelli Ron Zhu et al. 2021. The hateful memes challenge: Competition report. In NeurIPS 2020 Competition and Demonstration Track. PMLR 344--360."},{"key":"e_1_3_2_2_21_1","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems. 2611--2624","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 Proceedings of the 34th International Conference on Neural Information Processing Systems. 2611--2624."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander C Berg Wan-Yen Lo et al. 2023. Segment anything. arXiv preprint arXiv:2304.02643 (2023).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_2_23_1","volume-title":"ICML 2022 Workshop on Knowledge Retrieval and Language Models.","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 ICML 2022 Workshop on Knowledge Retrieval and Language Models."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478328"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475625"},{"key":"e_1_3_2_2_26_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_2_27_1","volume-title":"Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557","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. arXiv preprint arXiv:1908.03557 (2019)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.611"},{"key":"e_1_3_2_2_29_1","volume-title":"GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse. arXiv preprint arXiv:2401.01523","author":"Lin Hongzhan","year":"2024","unstructured":"Hongzhan Lin, Ziyang Luo, Bo Wang, Ruichao Yang, and Jing Ma. 2024. GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse. arXiv preprint arXiv:2401.01523 (2024)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.194"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.786"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25651"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. Springer, 740--755."},{"key":"e_1_3_2_2_34_1","volume-title":"A multimodal framework for the detection of hateful memes. arXiv preprint arXiv:2012.12871","author":"Lippe Phillip","year":"2020","unstructured":"Phillip Lippe, Nithin Holla, Shantanu Chandra, Santhosh Rajamanickam, Georgios Antoniou, Ekaterina Shutova, and Helen Yannakoudakis. 2020. A multimodal framework for the detection of hateful memes. arXiv preprint arXiv:2012.12871 (2020)."},{"key":"e_1_3_2_2_35_1","volume-title":"2023 a. Visual instruction tuning. arXiv preprint arXiv:2304.08485","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023 a. Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_2_2_37_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_2_38_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems. 13--23","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 Proceedings of the 33rd International Conference on Neural Information Processing Systems. 13--23."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.sigdial-1.28"},{"key":"e_1_3_2_2_40_1","volume-title":"Vilio: State-of-the-art visio-linguistic models applied to hateful memes. arXiv preprint arXiv:2012.07788","author":"Muennighoff Niklas","year":"2020","unstructured":"Niklas Muennighoff. 2020. Vilio: State-of-the-art visio-linguistic models applied to hateful memes. arXiv preprint arXiv:2012.07788 (2020)."},{"key":"e_1_3_2_2_41_1","volume-title":"Guy Gur-Ari, Henryk Michalewski, Jacob Austin, David Bieber, David Dohan, Aitor Lewkowycz, Maarten Bosma, David Luan, et al.","author":"Nye Maxwell","year":"2021","unstructured":"Maxwell Nye, Anders Johan Andreassen, Guy Gur-Ari, Henryk Michalewski, Jacob Austin, David Bieber, David Dohan, Aitor Lewkowycz, Maarten Bosma, David Luan, et al. 2021. Show your work: Scratchpads for intermediate computation with language models. arXiv preprint arXiv:2112.00114 (2021)."},{"key":"e_1_3_2_2_42_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. ArXiv Vol. abs\/2303.08774 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257532815"},{"key":"e_1_3_2_2_43_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, Vol. 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.246"},{"key":"e_1_3_2_2_45_1","volume-title":"Preslav Nakov, and Tanmoy Chakraborty.","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 Findings of the Association for Computational Linguistics: EMNLP 2021. 4439--4455."},{"key":"e_1_3_2_2_46_1","volume-title":"International conference on machine learning. 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. 8748--8763."},{"key":"e_1_3_2_2_47_1","unstructured":"Jack W Rae Sebastian Borgeaud Trevor Cai Katie Millican Jordan Hoffmann Francis Song John Aslanides Sarah Henderson Roman Ring Susannah Young et al. 2021. Scaling language models: Methods analysis & insights from training gopher. arXiv preprint arXiv:2112.11446 (2021)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_2_50_1","volume-title":"Detecting hateful memes using a multimodal deep ensemble. arXiv preprint arXiv:2012.13235","author":"Sandulescu Vlad","year":"2020","unstructured":"Vlad Sandulescu. 2020. Detecting hateful memes using a multimodal deep ensemble. arXiv preprint arXiv:2012.13235 (2020)."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/781"},{"key":"e_1_3_2_2_53_1","volume-title":"Proceedings of the second workshop on trolling, aggression and cyberbullying. 32--41","author":"Suryawanshi Shardul","year":"2020","unstructured":"Shardul Suryawanshi, Bharathi Raja Chakravarthi, Mihael Arcan, and Paul Buitelaar. 2020. Multimodal meme dataset (MultiOFF) for identifying offensive content in image and text. In Proceedings of the second workshop on trolling, aggression and cyberbullying. 32--41."},{"key":"e_1_3_2_2_54_1","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems-Volume 2. 3104--3112","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Proceedings of the 27th International Conference on Neural Information Processing Systems-Volume 2. 3104--3112."},{"key":"e_1_3_2_2_55_1","volume-title":"Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, et al.","author":"Thoppilan Romal","year":"2022","unstructured":"Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, et al. 2022. Lamda: Language models for dialog applications. arXiv preprint arXiv:2201.08239 (2022)."},{"key":"e_1_3_2_2_56_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_2_57_1","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 NIPS."},{"key":"e_1_3_2_2_58_1","volume-title":"Detecting hate speech in memes using multimodal deep learning approaches: Prize-winning solution to hateful memes challenge. arXiv preprint arXiv:2012.12975","author":"Velioglu Riza","year":"2020","unstructured":"Riza Velioglu and Jewgeni Rose. 2020. Detecting hate speech in memes using multimodal deep learning approaches: Prize-winning solution to hateful memes challenge. arXiv preprint arXiv:2012.12975 (2020)."},{"key":"e_1_3_2_2_59_1","volume-title":"Large language models are not fair evaluators. arXiv preprint arXiv:2305.17926","author":"Wang Peiyi","year":"2023","unstructured":"Peiyi Wang, Lei Li, Liang Chen, Dawei Zhu, Binghuai Lin, Yunbo Cao, Qi Liu, Tianyu Liu, and Zhifang Sui. 2023. Large language models are not fair evaluators. arXiv preprint arXiv:2305.17926 (2023)."},{"key":"e_1_3_2_2_60_1","volume-title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models. In The Eleventh International Conference on Learning Representations.","author":"Wang Xuezhi","year":"2022","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. Self-Consistency Improves Chain of Thought Reasoning in Language Models. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_2_61_1","volume-title":"Quoc V Le, Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed H Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_62_1","volume-title":"Answering questions by meta-reasoning over multiple chains of thought. arXiv preprint arXiv:2304.13007","author":"Yoran Ori","year":"2023","unstructured":"Ori Yoran, Tomer Wolfson, Ben Bogin, Uri Katz, Daniel Deutch, and Jonathan Berant. 2023. Answering questions by meta-reasoning over multiple chains of thought. arXiv preprint arXiv:2304.13007 (2023)."},{"key":"e_1_3_2_2_63_1","volume-title":"Automatic chain of thought prompting in large language models. arXiv preprint arXiv:2210.03493","author":"Zhang Zhuosheng","year":"2022","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. 2022. Automatic chain of thought prompting in large language models. arXiv preprint arXiv:2210.03493 (2022)."},{"key":"e_1_3_2_2_64_1","volume-title":"Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923","author":"Zhang Zhuosheng","year":"2023","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, and Alex Smola. 2023. Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923 (2023)."},{"key":"e_1_3_2_2_65_1","volume-title":"Progressive-hint prompting improves reasoning in large language models. arXiv preprint arXiv:2304.09797","author":"Zheng Chuanyang","year":"2023","unstructured":"Chuanyang Zheng, Zhengying Liu, Enze Xie, Zhenguo Li, and Yu Li. 2023. Progressive-hint prompting improves reasoning in large language models. arXiv preprint arXiv:2304.09797 (2023)."},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455994"},{"key":"e_1_3_2_2_67_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)."},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3501247.3531557"},{"key":"e_1_3_2_2_69_1","volume-title":"Enhance multimodal transformer with external label and in-domain pretrain: Hateful meme challenge winning solution. arXiv preprint arXiv:2012.08290","author":"Zhu Ron","year":"2020","unstructured":"Ron Zhu. 2020. Enhance multimodal transformer with external label and in-domain pretrain: Hateful meme challenge winning solution. arXiv preprint arXiv:2012.08290 (2020)."}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645381","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589334.3645381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:30:19Z","timestamp":1755822619000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645381"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":69,"alternative-id":["10.1145\/3589334.3645381","10.1145\/3589334"],"URL":"https:\/\/doi.org\/10.1145\/3589334.3645381","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}