CoChat
Sign Up
Cited by 20Multimodal Machine Learning ApplicationsHate Speech and Cyberbullying DetectionTopic Modeling

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

MM-SOC: Benchmarking Multimodal Large Language Models in Social Media Platforms

Open access
Jin, Yiqiao, Choi, Minje, Verma, Gaurav, Wang, Jindong, Kumar, Srijan·2024·Findings of the Association for Computational Linguistics ACL 2024
DOI 10.18653/v1/2024.findings-acl.370
Open this paper in CoChat — free accountOpen PDF

Abstract

Social media platforms are hubs for multimodal information exchange, encompassing text, images, and videos, making it challenging for machines to comprehend the information or emotions associated with interactions in online spaces.Multimodal Large Language Models (MLLMs) have emerged as a promising solution to these challenges, yet they struggle to accurately interpret human emotions and complex content such as misinformation.This paper introduces MM-SOC, a comprehensive benchmark designed to evaluate MLLMs' understanding of multimodal social media content.MM-SOC compiles prominent multimodal datasets and incorporates a novel large-scale YouTube tagging dataset, targeting a range of tasks from misinformation detection, hate speech detection, and social context generation.Through our exhaustive evaluation on ten size-variants of four opensource MLLMs, we have identified significant performance disparities, highlighting the need for advancements in models' social understanding capabilities.Our analysis reveals that, in a zero-shot setting, various types of MLLMs generally exhibit difficulties in handling social media tasks.However, MLLMs demonstrate performance improvements post fine-tuning, suggesting potential pathways for improvement.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/2024.findings-acl.370

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Recent works evaluating VLMs for embodied and online scenarios primarily focus on perception tasks rather than long-horizon decision making.

    “Recent works evaluating VLMs for embodied and online scenarios [86–91] primarily focus on perception tasks rather than long-horizon decision making.”

    From Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making (2024) · cites this paper as [90]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 76

  1. Hala Al Kuwatly, Maximilian Wich, and Georg Groh. 2020. Identifying and measuring annotator bias based on annotators' demographic characteristics. In Proceedings of the Fourth Workshop on Online Abuse and Harms, pages 184-190, Online. Association for Computational Linguistics. · DOI
  2. Sharifa Alghowinem, Roland Goecke, Michael Wag- ner, Julien Epps, Matthew Hyett, Gordon Parker, and Michael Breakspear. 2016. Multimodal depression detection: fusion analysis of paralinguistic, head pose and eye gaze behaviors. IEEE Transactions on Affec- tive Computing, 9(4):478-490.
  3. Lora Aroyo and Chris Welty. 2015. Truth is a lie: Crowd truth and the seven myths of human annotation. AI Magazine, 36(1):15-24.
  4. Anas Awadalla, Irena Gao, Josh Gardner, Jack Hes- sel, Yusuf Hanafy, Wanrong Zhu, Kalyani Marathe, Yonatan Bitton, Samir Gadre, Shiori Sagawa, et al. 2023. Openflamingo: An open-source framework for training large autoregressive vision-language models. arXiv:2308.01390. · arXiv
  5. Chunkit Chan, Jiayang Cheng, Weiqi Wang, Yuxin Jiang, Tianqing Fang, Xin Liu, and Yangqiu Song. 2023. Chatgpt evaluation on sentence level relations: A focus on temporal, causal, and discourse relations. arXiv:2304.14827. · arXiv
  6. Canyu Chen and Kai Shu. 2023a. Can llm-generated misinformation be detected? arXiv:2309.13788. · arXiv
  7. Canyu Chen and Kai Shu. 2023b. Combating misinfor- mation in the age of llms: Opportunities and chal- lenges. arXiv:2311.05656. · arXiv
  8. Minje Choi, Jiaxin Pei, Sagar Kumar, Chang Shu, and David Jurgens. 2023. Do llms understand social knowledge? evaluating the sociability of large lan- guage models with socket benchmark. In EMNLP 2023.
  9. W Dai, J Li, D Li, AMH Tiong, J Zhao, W Wang, B Li, P Fung, and S Hoi. 2023. Instructblip: To- wards general-purpose vision-language models with instruction tuning. arxiv 2023. arXiv:2305.06500. · arXiv
  10. Aniket Deroy, Kripabandhu Ghosh, and Saptarshi Ghosh. 2023. How ready are pre-trained abstractive models and llms for legal case judgement summariza- tion? arXiv:2306.01248. · arXiv
  11. Tao Fan, Yan Kang, Guoqiang Ma, Weijing Chen, Wen- bin Wei, Lixin Fan, and Qiang Yang. 2023. Fate-llm: A industrial grade federated learning framework for large language models. arXiv:2310.10049. · arXiv
  12. Emilio Ferrara. 2020. Dynamics of Attention and Public Opinion in Social Media. In The Oxford Handbook of Networked Communication. Oxford University Press. · DOI
  13. Peng Gao, Jiaming Han, Renrui Zhang, Ziyi Lin, Shi- jie Geng, Aojun Zhou, Wei Zhang, Pan Lu, Con- ghui He, Xiangyu Yue, et al. 2023. Llama-adapter v2: Parameter-efficient visual instruction model. arXiv:2304.15010. · arXiv
  14. Bing He, Yibo Hu, Yeon-Chang Lee, Soyoung Oh, Gaurav Verma, and Srijan Kumar. 2023. A sur- vey on the role of crowds in combating online mis- information: Annotators, evaluators, and creators. arXiv:2310.02095. · arXiv
  15. Bing He, Caleb Ziems, Sandeep Soni, Naren Ramakrish- nan, Diyi Yang, and Srijan Kumar. 2021. Racism is a virus: Anti-asian hate and counterspeech in social media during the covid-19 crisis. In ASONAM, pages 90-94.
  16. Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2020. Deberta: Decoding-enhanced bert with disentangled attention. In ICLR.
  17. Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2019. The curious case of neural text degeneration. In ICLR.
  18. Jianheng Huang, Leyang Cui, Ante Wang, Chengyi Yang, Xinting Liao, Linfeng Song, Junfeng Yao, and Jinsong Su. 2024. Mitigating catastrophic forget- ting in large language models with self-synthesized rehearsal. arXiv:2403.01244. · arXiv
  19. Lora L Jacobi. 2014. Perceptions of profanity: How race, gender, and expletive choice affect perceived of- fensiveness. North American Journal of Psychology, 16(2).
  20. Sepehr Janghorbani and Gerard De Melo. 2023. Multi- modal bias: Introducing a framework for stereo- typical bias assessment beyond gender and race in vision-language models. In EACL, pages 1725-1735, Dubrovnik, Croatia. Association for Computational Linguistics. · DOI
  21. Yiqiao Jin, Mohit Chandra, Gaurav Verma, Yibo Hu, Munmun De Choudhury, and Srijan Kumar. 2023. Better to ask in english: Cross-lingual evaluation of large language models for healthcare queries. arXiv e-prints, pages arXiv-2310.
  22. Yiqiao Jin, Xiting Wang, Ruichao Yang, Yizhou Sun, Wei Wang, Hao Liao, and Xing Xie. 2022. Towards fine-grained reasoning for fake news detection. In AAAI, volume 36, pages 5746-5754.
  23. Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirec- tional transformers for language understanding. In NAACL, pages 4171-4186.
  24. Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, and Davide Testuggine. 2020. The hateful memes chal- lenge: Detecting hate speech in multimodal memes. NeurIPS, 33:2611-2624.
  25. Grzegorz Kondrak. 2005. N-gram similarity and dis- tance. In International symposium on string pro- cessing and information retrieval, pages 115-126.
  26. Alon Lavie, Kenji Sagae, and Shyamsundar Jayaraman. 2004. The significance of recall in automatic met- rics for mt evaluation. In AMTA, pages 134-143.
  27. Vladimir I Levenshtein et al. 1966. Binary codes capa- ble of correcting deletions, insertions, and reversals. In Soviet physics doklady, volume 10, pages 707-710.
  28. Cheng Li, Jindong Wang, Yixuan Zhang, Kaijie Zhu, Xinyi Wang, Wenxin Hou, Jianxun Lian, Fang Luo, Qiang Yang, and Xing Xie. 2023a. The good, the bad, and why: Unveiling emotions in generative ai. arXiv:2312.11111. · arXiv
  29. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023b. Blip-2: Bootstrapping language-image pre- training with frozen image encoders and large lan- guage models. arXiv:2301.12597. · arXiv
  30. Shanglin Li, Bohan Zeng, Yutang Feng, Sicheng Gao, Xuhui Liu, Jiaming Liu, Li Lin, Xu Tang, Yao Hu, Jianzhuang Liu, et al. 2023c. Zone: Zero-shot instruction-guided local editing. arXiv:2312.16794. · arXiv
  31. Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74-81.
  32. Fuxiao Liu, Xiaoyang Wang, Wenlin Yao, Jianshu Chen, Kaiqiang Song, Sangwoo Cho, Yaser Yacoob, and Dong Yu. 2023a. Mmc: Advancing multimodal chart understanding with large-scale instruction tun- ing. arXiv:2311.10774. · arXiv
  33. Fuxiao Liu, Yinghan Wang, Tianlu Wang, and Vicente Ordonez. 2020. Visual news: Benchmark and chal- lenges in news image captioning. arXiv:2010.03743. · arXiv
  34. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2023b. Improved baselines with visual instruc- tion tuning. In NeurIPS 2023 Workshop on Instruc- tion Tuning and Instruction Following.
  35. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023c. Visual instruction tuning. arXiv:2304.08485. · arXiv
  36. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Man- dar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining ap- proach. arXiv:1907.11692. · arXiv
  37. Edward Loper and Steven Bird. 2002. Nltk: the natu- ral language toolkit. In Proceedings of the ACL-02 Workshop on Effective tools and methodologies for teaching natural language processing and computa- tional linguistics-Volume 1, pages 63-70.
  38. Jiachen Ma, Yong Liu, Meng Liu, and Meng Han. 2022. Curriculum contrastive learning for fake news detec- tion. In CIKM, pages 4309-4313.
  39. Mainack Mondal, Leandro Araújo Silva, and Fabrício Benevenuto. 2017. A measurement study of hate speech in social media. In ACM Hypertext, pages 85-94.
  40. Kishore Papineni, Salim Roukos, Todd Ward, and Wei- Jing Zhu. 2002. Bleu: a method for automatic evalua- tion of machine translation. In ACL, pages 311-318.
  41. Bowen Peng, Jeffrey Quesnelle, Honglu Fan, and Enrico Shippole. 2023. Yarn: Efficient context window ex- tension of large language models. arXiv:2309.00071. · arXiv
  42. Alexander Peysakhovich and Adam Lerer. 2023. At- tention sorting combats recency bias in long context language models. arXiv:2310.01427. · arXiv
  43. Inioluwa Deborah Raji, Emily Denton, Emily M Bender, Alex Hanna, and Amandalynne Paullada. 2021. Ai and the everything in the whole wide world bench- mark. In Thirty-fifth Conference on Neural Informa- tion Processing Systems Datasets and Benchmarks Track (Round 2).
  44. Rita Ramos, Desmond Elliott, and Bruno Martins. 2023. Retrieval-augmented image captioning. In EACL, pages 3666-3681, Dubrovnik, Croatia. Association for Computational Linguistics. · DOI
  45. Nils Reimers and Iryna Gurevych. 2019. Sentence- BERT: Sentence embeddings using Siamese BERT- networks. In EMNLP-IJCNLP, pages 3982-3992, Hong Kong, China. Association for Computational Linguistics. · DOI · Paper page
  46. Gabriele Ruggeri and Debora Nozza. 2023. A multi- dimensional study on bias in vision-language models. In Findings of the Association for Computational Linguistics: ACL 2023, pages 6445-6455, Toronto, Canada. Association for Computational Linguistics. · DOI
  47. Jaromir Savelka, Kevin D Ashley, Morgan A Gray, Hannes Westermann, and Huihui Xu. 2023. Can gpt-4 support analysis of textual data in tasks requiring highly specialized domain expertise? arXiv:2306.13906. · arXiv
  48. Chhavi Sharma, Deepesh Bhageria, William Scott, Srinivas Pykl, Amitava Das, Tanmoy Chakraborty, Viswanath Pulabaigari, and Björn Gambäck. 2020. Semeval-2020 task 8: Memotion analysis-the visuo- lingual metaphor! In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 759-773.
  49. Bangzhao Shu, Lechen Zhang, Minje Choi, Lavinia Dunagan, Dallas Card, and David Jurgens. 2023. You don't need a personality test to know these models are unreliable: Assessing the reliability of large language models on psychometric instruments. arXiv:2311.09718. · arXiv
  50. Kai Shu, Deepak Mahudeswaran, Suhang Wang, Dong- won Lee, and Huan Liu. 2020. Fakenewsnet: A data repository with news content, social context, and spa- tiotemporal information for studying fake news on social media. Big data, 8(3):171-188.
  51. Maria Grazia Sindoni. 2020. '# youcantalk': A multi- modal discourse analysis of suicide prevention and peer support in the australian beyondblue platform. Discourse & Communication, 14(2):202-221.
  52. Huaman Sun, Jiaxin Pei, Minje Choi, and David Jurgens. 2023. Aligning with whom? large language models have gender and racial biases in subjective nlp tasks. arXiv:2311.09730. · arXiv
  53. Gaurav Verma, Ryan A Rossi, Christopher Tensmeyer, Jiuxiang Gu, and Ani Nenkova. 2023. Learning the visualness of text using large vision-language models. In EMNLP.
  54. Soroush Vosoughi, Deb Roy, and Sinan Aral. 2018. The spread of true and false news online. science, 359(6380):1146-1151.
  55. Weiqi Wang, Tianqing Fang, Chunyang Li, Haochen Shi, Wenxuan Ding, Baixuan Xu, Zhaowei Wang, Jiaxin Bai, Xin Liu, Jiayang Cheng, et al. 2024a. Candle: Iterative conceptualization and instantiation distillation from large language models for common- sense reasoning. arXiv:2401.07286. · arXiv
  56. Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. Minilm: Deep self- attention distillation for task-agnostic compression of pre-trained transformers. NeurIPS, 33:5776-5788.
  57. Xiyao Wang, Yuhang Zhou, Xiaoyu Liu, Hongjin Lu, Yuancheng Xu, Feihong He, Jaehong Yoon, Taixi Lu, Gedas Bertasius, Mohit Bansal, et al. 2024b. Mementos: A comprehensive benchmark for mul- timodal large language model reasoning over image sequences. arXiv:2401.10529. · arXiv
  58. Zhaowei Wang, Haochen Shi, Weiqi Wang, Tianqing Fang, Hongming Zhang, Sehyun Choi, Xin Liu, and Yangqiu Song. 2023. Abspyramid: Benchmarking the abstraction ability of language models with a unified entailment graph. arXiv:2311.09174. · arXiv
  59. Zeerak Waseem. 2016. Are you a racist or am i seeing things? annotator influence on hate speech detection on twitter. In Proceedings of the first workshop on NLP and computational social science, pages 138- 142.
  60. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier- ric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, et al. 2020. Transformers: State-of-the-art natural language processing. In EMNLP, pages 38-45.
  61. Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xian- jun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Haifeng Chen, et al. 2023. Large lan- guage models can be good privacy protection learners. arXiv:2310.02469. · arXiv
  62. Chengxing Xie, Canyu Chen, Feiran Jia, Ziyu Ye, Kai Shu, Adel Bibi, Ziniu Hu, Philip Torr, Bernard Ghanem, and Guohao Li. 2024. Can large lan- guage model agents simulate human trust behaviors? arXiv:2402.04559. · arXiv
  63. Pingping Yang, Jiachen Ma, Yong Liu, and Meng Liu. 2023. Multi-modal transformer for fake news detec- tion. Mathematical Biosciences and Engineering: MBE, 20(8):14699-14717.
  64. Ruichao Yang, Xiting Wang, Yiqiao Jin, Chaozhuo Li, Jianxun Lian, and Xing Xie. 2022. Reinforcement subgraph reasoning for fake news detection. In KDD, pages 2253-2262.
  65. Weihao Yu, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Xinchao Wang, and Lijuan Wang. 2023. Mm-vet: Evaluating large multimodal models for integrated capabilities. arXiv:2308.02490. · arXiv
  66. Savvas Zannettou, Tristan Caulfield, Jeremy Blackburn, Emiliano De Cristofaro, Michael Sirivianos, Gian- luca Stringhini, and Guillermo Suarez-Tangil. 2018. On the origins of memes by means of fringe web communities. In ACM IMC, IMC '18, page 188-202, New York, NY, USA. Association for Computing Machinery. · DOI
  67. Bohan Zeng, Shanglin Li, Yutang Feng, Hong Li, Sicheng Gao, Jiaming Liu, Huaxia Li, Xu Tang, Jianzhuang Liu, and Baochang Zhang. 2023. Ip- dreamer: Appearance-controllable 3d object genera- tion with image prompts. arXiv:2310.05375. · arXiv
  68. Yuexiang Zhai, Shengbang Tong, Xiao Li, Mu Cai, Qing Qu, Yong Jae Lee, and Yi Ma. 2024. Investigating the catastrophic forgetting in multimodal large language model fine-tuning. In Conference on Parsimony and Learning, pages 202-227. PMLR.
  69. Peiyan Zhang, Haoyang Liu, Chaozhuo Li, Xing Xie, Sunghun Kim, and Haohan Wang. 2023a. Foundation model-oriented robustness: Robust image model evaluation with pretrained models. arXiv:2308.10632. · arXiv
  70. Renrui Zhang, Jiaming Han, Aojun Zhou, Xiangfei Hu, Shilin Yan, Pan Lu, Hongsheng Li, Peng Gao, and Yu Qiao. 2023b. Llama-adapter: Efficient fine- tuning of language models with zero-init attention. arXiv:2303.16199. · arXiv
  71. Zhuo Zhang, Yuanhang Yang, Yong Dai, Qifan Wang, Yue Yu, Lizhen Qu, and Zenglin Xu. 2023c. Fed- petuning: When federated learning meets the parameter-efficient tuning methods of pre-trained lan- guage models. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9963- 9977.
  72. Qinlin Zhao, Jindong Wang, Yixuan Zhang, Yiqiao Jin, Kaijie Zhu, Hao Chen, and Xing Xie. 2023. Competeai: Understanding the competition be- haviors in large language model-based agents. arXiv:2310.17512. · arXiv
  73. Peilin Zhou, Meng Cao, You-Liang Huang, Qichen Ye, Peiyan Zhang, Junling Liu, Yueqi Xie, Yining Hua, and Jaeboum Kim. 2023. Exploring recommendation capabilities of gpt-4v (ision): A preliminary case study. arXiv:2311.04199. · arXiv
  74. Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023a. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv:2304.10592. · arXiv
  75. Kaijie Zhu, Jindong Wang, Jiaheng Zhou, Zichen Wang, Hao Chen, Yidong Wang, Linyi Yang, Wei Ye, Neil Zhenqiang Gong, Yue Zhang, et al. 2023b. Promptbench: Towards evaluating the robustness of large language models on adversarial prompts. arXiv:2306.04528. · arXiv
  76. Qing Zong, Zhaowei Wang, Baixuan Xu, Tianshi Zheng, Haochen Shi, Weiqi Wang, Yangqiu Song, Ginny Y Wong, and Simon See. 2023. Tilfa: A unified frame- work for text, image, and layout fusion in argument mining. EMNLP 2023, page 139.

Cited by

Sorted by citations

Metadata

Authors
Jin, Y., Choi, M., Verma, G., Wang, J., & Kumar, S.
Affiliations
  • Georgia Institute of Technology (US)
  • Microsoft Research Asia (China) (CN)
ORCID
Venue
Findings of the Association for Computational Linguistics ACL 2024
Publisher
Association for Computational Linguistics
Published
2024
Pages
6192-6210
DOI
10.18653/v1/2024.findings-acl.370
OpenAlex
W4402683906
Cited by
20
References
1
Citations by year
2026: 8 · 2025: 7 · 2024: 5
FWCI
3.73
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • Findings of the Association for Computational Linguistics: ACL (Findings of ACL) (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
Funders
  • National Science Foundation (2137724, 2154118, 2239879, 2230692)
  • Centers for Disease Control and Prevention
  • Defense Advanced Research Projects Agency (HR00112290102)
  • Advanced Research Projects Agency
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
Keywords
multimodal large language models, benchmark, misinformation detection, hate speech detection, emotional understanding, zero-shot performance, fine-tuning, model size comparison

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review