Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models
Authors: 
Hongzhan Lin, Ziyang Luo, Wei Gao, Jing Ma, Bo Wang, Ruichao YangAuthors Info & Claims
Pages 2359 - 2370
Abstract
The age of social media is flooded with Internet memes, necessitating a clear grasp and effective identification of harmful ones. This task presents a significant challenge due to the implicit meaning embedded in memes, which is not explicitly conveyed through the surface text and image. However, existing harmful meme detection methods do not present readable explanations that unveil such implicit meaning to support their detection decisions. In this paper, we propose an explainable approach to detect harmful memes, achieved through reasoning over conflicting rationales from both harmless and harmful positions. Specifically, inspired by the powerful capacity of Large Language Models (LLMs) on text generation and reasoning, we first elicit multimodal debate between LLMs to generate the explanations derived from the contradictory arguments. Then we propose to fine-tune a small language model as the debate judge for harmfulness inference, to facilitate multimodal fusion between the harmfulness rationales and the intrinsic multimodal information within memes. In this way, our model is empowered to perform dialectical reasoning over intricate and implicit harm-indicative patterns, utilizing multimodal explanations originating from both harmless and harmful arguments. Extensive experiments on three public meme datasets demonstrate that our harmful meme detection approach achieves much better performance than state-of-the-art methods and exhibits a superior capacity for explaining the meme harmfulness of the model predictions.
Supplemental Material
MP4 File
presentation video
- Download
- 1310.61 MB
MP4 File
Supplemental video
- Download
- 55.75 MB
References
[1]
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).
[2]
Michael Basseches. 1984. Dialectical thinking. Norwood, NJ: Ablex (1984).
[3]
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.
[4]
Rui Cao, Ming Shan Hee, Adriel Kuek, Wen-Haw Chong, Roy Ka-Wei Lee, and Jing Jiang. 2023. Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection. In Proceedings of the 31th ACM international conference on multimedia.
[5]
Rui Cao, Roy Ka-Wei Lee, Wen-Haw Chong, and Jing Jiang. 2022. Prompting for Multimodal Hateful Meme Classification. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 321--332.
[6]
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).
[7]
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).
[8]
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).
[9]
Abhishek Das, Japsimar Singh Wahi, and Siyao Li. 2020. Detecting hate speech in multi-modal memes. arXiv preprint arXiv:2012.14891 (2020).
[10]
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.
[11]
Alexander R Fabbri, Wojciech Kry'sci'nski, Bryan McCann, Caiming Xiong, Richard Socher, and Dragomir Radev. 2021. Summeval: Re-evaluating summarization evaluation. Transactions of the Association for Computational Linguistics, Vol. 9 (2021), 391--409.
[12]
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.
[13]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770--778.
[14]
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).
[15]
Ming Shan Hee, Roy Ka-Wei Lee, and Wen-Haw Chong. 2022. On Explaining Multimodal Hateful Meme Detection Models. In Proceedings of the ACM Web Conference 2022. 3651--3655.
[16]
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).
[17]
Junhui Ji, Wei Ren, and Usman Naseem. 2023 b. Identifying Creative Harmful Memes via Prompt based Approach. In Proceedings of the ACM Web Conference 2023. 3868--3872.
[18]
Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023 a. Survey of hallucination in natural language generation. Comput. Surveys, Vol. 55, 12 (2023), 1--38.
[19]
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).
[20]
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.
[21]
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.
[22]
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).
[23]
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.
[24]
Zhanghui Kuang, Hongbin Sun, Zhizhong Li, Xiaoyu Yue, Tsui Hin Lin, Jianyong Chen, Huaqiang Wei, Yiqin Zhu, Tong Gao, Wenwei Zhang, et al. 2021. MMOCR: a comprehensive toolbox for text detection, recognition and understanding. In Proceedings of the 29th ACM International Conference on Multimedia. 3791--3794.
[25]
Roy Ka-Wei Lee, Rui Cao, Ziqing Fan, Jing Jiang, and Wen-Haw Chong. 2021. Disentangling hate in online memes. In Proceedings of the 29th ACM International Conference on Multimedia. 5138--5147.
[26]
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).
[27]
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).
[28]
Hongzhan Lin, Ziyang Luo, Jing Ma, and Long Chen. 2023 a. Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models. In The 2023 Conference on Empirical Methods in Natural Language Processing.
[29]
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).
[30]
Hongzhan Lin, Jing Ma, Liangliang Chen, Zhiwei Yang, Mingfei Cheng, and Chen Guang. 2022. Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive Learning. In Findings of the Association for Computational Linguistics: NAACL 2022. 2543--2556.
[31]
Hongzhan Lin, Jing Ma, Mingfei Cheng, Zhiwei Yang, Liangliang Chen, and Guang Chen. 2021. Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 10035--10047.
[32]
Hongzhan Lin, Pengyao Yi, Jing Ma, Haiyun Jiang, Ziyang Luo, Shuming Shi, and Ruifang Liu. 2023 b. Zero-shot rumor detection with propagation structure via prompt learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37. 5213--5221.
[33]
Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, 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.
[34]
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).
[35]
Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023 a. Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023).
[36]
Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023 b. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. Comput. Surveys, Vol. 55, 9 (2023), 1--35.
[37]
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).
[38]
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.
[39]
Shikib Mehri and Maxine Eskenazi. 2020. Unsupervised Evaluation of Interactive Dialog with DialoGPT. In Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 225--235.
[40]
Niklas Muennighoff. 2020. Vilio: State-of-the-art visio-linguistic models applied to hateful memes. arXiv preprint arXiv:2012.07788 (2020).
[41]
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).
[42]
OpenAI. 2023. GPT-4 Technical Report. ArXiv, Vol. abs/2303.08774 (2023). https://api.semanticscholar.org/CorpusID:257532815
[43]
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.
[44]
Shraman Pramanick, Dimitar Dimitrov, Rituparna Mukherjee, Shivam Sharma, Md Shad Akhtar, Preslav Nakov, and Tanmoy Chakraborty. 2021a. Detecting Harmful Memes and Their Targets. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 2783--2796.
[45]
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.
[46]
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.
[47]
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).
[48]
Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research, Vol. 21, 1 (2020), 5485--5551.
[49]
Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2016. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, 6 (2016), 1137--1149.
[50]
Vlad Sandulescu. 2020. Detecting hateful memes using a multimodal deep ensemble. arXiv preprint arXiv:2012.13235 (2020).
[51]
Piyush Sharma, Nan Ding, Sebastian Goodman, and Radu Soricut. 2018. Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2556--2565.
[52]
Shivam Sharma, Firoj Alam, Md Shad Akhtar, Dimitar Dimitrov, Giovanni Da San Martino, Hamed Firooz, Alon Halevy, Fabrizio Silvestri, Preslav Nakov, and Tanmoy Chakraborty. 2022. Detecting and understanding harmful memes: A survey. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. 5597--5606.
[53]
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.
[54]
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.
[55]
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).
[56]
Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023).
[57]
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.
[58]
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).
[59]
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).
[60]
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.
[61]
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.
[62]
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).
[63]
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).
[64]
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).
[65]
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).
[66]
Yi Zhou, Zhenhao Chen, and Huiyuan Yang. 2021. Multimodal learning for hateful memes detection. In 2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). IEEE, 1--6.
[67]
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).
[68]
Jiawen Zhu, Roy Ka-Wei Lee, and Wen Haw Chong. 2022. Multimodal zero-shot hateful meme detection. In 14th ACM Web Science Conference 2022. 382--389.
[69]
Ron Zhu. 2020. Enhance multimodal transformer with external label and in-domain pretrain: Hateful meme challenge winning solution. arXiv preprint arXiv:2012.08290 (2020).
Index Terms
- Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models
Recommendations
On Explaining Multimodal Hateful Meme Detection Models
WWW '22: Proceedings of the ACM Web Conference 2022Hateful meme detection is a new multimodal task that has gained significant traction in academic and industry research communities. Recently, researchers have applied pre-trained visual-linguistic models to perform the multimodal classification task, ...
How Challenging is Multimodal Irony Detection?
Natural Language Processing and Information SystemsAbstractThe possibility that social networks offer to attach audio, video, and images to textual information has led many users to create messages with multimodal irony. Over the last years, a series of approaches have emerged trying to leverage all these ...
Identifying textual disinformation using Large Language Models
CHIIR '24: Proceedings of the 2024 Conference on Human Information Interaction and RetrievalThe spread of disinformation is becoming a more acute challenge in modern society. The rise of AI technologies is providing it with an additional boost, making disinformation creation and propagation available to almost anyone. This change in the ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
May 2024
4826 pages
ISBN:9798400701719
DOI:10.1145/3589334
- General Chairs:
- Tat-Seng Chua,
- Chong-Wah Ngo,
- Proceedings Chair:
- Roy Ka-Wei Lee,
- Program Chairs:
- Ravi Kumar,
- Hady W. Lauw
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 13 May 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
WWW '24
Sponsor:
Acceptance Rates
Overall Acceptance Rate 1,899 of 8,196 submissions, 23%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 790Total Downloads
- Downloads (Last 12 months)790
- Downloads (Last 6 weeks)230
Reflects downloads up to 21 Nov 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in