Elamur Research⌕
☰
home / papers / 2026 / Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs

Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs

Paper · 2026 · Chi Zhang, Wenxuan Ding, Jiale Liu et al.

Summary

The paper asks how vision-language models handle a conflict between what an image shows and what accompanying text claims. To study this, the authors build CONTEXT-VQA from A-OKVQA. They recast questions as multiple choice and keep only items that every tested model already answers correctly. This isolates the effect of manipulation from question difficulty. For each item, the most plausible wrong option becomes a false claim. Gemini 2.5-Pro then writes persuasive arguments for that claim, which the authors check by hand. A multi-round evaluation tracks answer changes and confidence shifts across 11 open-source and proprietary VLMs. The models prove highly susceptible: after a single persuasive turn, accuracy falls by more than 48.2% on average. Models frequently abandon clear visual evidence and adopt the wrong answer with confidence. A simple system-prompt warning to trust the image recovers part of the loss. The work exposes a reliability gap that matters for safety-critical uses such as driving, content moderation and medical imaging.

Key points

  • Dataset construction: The authors sampled 2,000 A-OKVQA image-question pairs. Filtering to items all models solved left 920 questions. The misleading target is the distractor with the second-highest average confidence.
  • Persuasion strategies: Four types are used:
    • repetition,
    • logical appeal (misreading visual details),
    • credibility appeal (posing as an authority),
    • emotional appeal.
  • Main result: Across 11 state-of-the-art VLMs, accuracy drops by more than 48.2% on average after one round of persuasion.
  • Prompt-based defense: An "alarm" system prompt urging consistency with the image helped all four proprietary models tested. Average accuracy rose by 8.6 points for Gemini 2.5-Flash (27.4 → 36.0), 6.6 for GPT-4o-mini, 4.7 for GPT-4o and 4.4 for Gemini 2.5-Pro. The largest gains came against repetition, for example +16.3 for GPT-4o-mini.
  • Stated limitations:
    • The benchmark is small because of budget constraints.
    • The internal causes of the behavior are not analysed.
    • Defenses based on architecture or fine-tuning are left for future work.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓New York UniversityNew York · United States201 works · 100,180 citations🎓The University of Texas at AustinAustin · United States109 works · 56,942 citations🎓University of Chinese Academy of SciencesBeijing · China147 works · 8,480 citations🎓Pennsylvania State UniversityState College · United States56 works · 5,360 citations

 Fields, topics and concepts

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 worksSocial Sciences · 1,772 worksSociology and Political Science · 577 works

Cite

Cite as Chi Zhang, Wenxuan Ding, Jiale Liu, Mingrui Wu, Qingyun Wu and Ray Mooney. 2026. Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.eacl-long.323

@inproceedings{zhang2026do,
  title = {{Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs}},
  author = {Chi Zhang, Wenxuan Ding, Jiale Liu, Mingrui Wu, Qingyun Wu and Ray Mooney},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-long.323},
  url = {https://doi.org/10.18653/v1/2026.eacl-long.323}
}

References

74 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Nouar AlDahoul, Myles Joshua Toledo Tan, Harish-war Reddy Kasireddy, and Yasir Zaki. 2024. Advancing content moderation: Evaluating large language models for detecting sensitive content across text, images, and videos. arXiv preprint arXiv:2411.17123. — [arXiv:2411.17123](https://arxiv.org/abs/2411.17123) find
  2. Zechen Bai, Pichao Wang, Tianjun Xiao, Tong He, Zongbo Han, Zheng Zhang, and Mike Zheng Shou. 2024. Hallucination of multimodal large language models: A survey. arXiv preprint arXiv:2404.18930.
  3. Yejin Bang, Samuel Cahyawijaya, Nayeon Lee, Wenliang Dai, Dan Su, Bryan Wilie, Holy Lovenia, Ziwei Ji, Tiezheng Yu, Willy Chung, and 1 others. 2023. A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. In Proceedings of the 13th International Jo…
  4. Nicholas Carlini, Milad Nasr, Christopher A. Choquette-Choo, Matthew Jagielski, Irena Gao, Pang Wei Koh, Daphne Ippolito, Florian Tramèr, and Ludwig Schmidt. 2023. Are aligned neural networks adversarially aligned? In Thirty-seventh Conference on Neural Information Processing Systems. find
  5. Lizhang Chen, Jonathan Li, Kaizhao Liang, Baiyu Su, Cong Xie, Nuo Wang Pierse, Chen Liang, Ni Lao, and Qiang Liu. 2025. Cautious weight decay. arXiv preprint arXiv:2510.12402. — [arXiv:2510.12402](https://arxiv.org/abs/2510.12402) find
  6. Lizhang Chen, Bo Liu, Kaizhao Liang, and Qiang Liu. 2024a. Lion secretly solves constrained optimization: As lyapunov predicts. International Conference on Learning Representations, Spotlight. find
  7. Lizhang Chen, Bo Liu, Lemeng Wu, Kaizhao Liang, Jiaxu Zhu, Chen Liang, Raghuraman Krishnamoorthi, and Qiang Liu. 2024b. Communication efficient distributed training with distributed lion. Advances in Neural Information Processing Systems, 37:18388– 18415. find
  8. Zhe Chen, Weiyun Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Erfei Cui, Jinguo Zhu, Shenglong Ye, Hao Tian, Zhaoyang Liu, and 1 others. 2024c. Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271.
  9. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, and 1 others. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arX…
  10. Edoardo Debenedetti, Jie Zhang, Mislav Balunovi’c, Luca Beurer-Kellner, Marc Fischer, and Florian Tramèr. 2024. Agentdojo: A dynamic environment to evaluate attacks and defenses for llm agents. ArXiv, abs/2406.13352. — [arXiv:2406.13352](https://arxiv.org/abs/2406.13352) find
  11. Wenxuan Ding, Shangbin Feng, Yuhan Liu, Zhaoxuan Tan, Vidhisha Balachandran, Tianxing He, and Yulia Tsvetkov. 2024. Knowledge crosswords: Geometric knowledge reasoning with large language models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2609–2636. find
  12. Jiwei Guan, Tianyu Ding, Longbing Cao, Lei Pan, Chen Wang, and Xi Zheng. 2024a. Probing the robustness of vision-language pretrained models: A multimodal adversarial attack approach. arXiv preprint arXiv:2408.13461. — [arXiv:2408.13461](https://arxiv.org/abs/2408.13461) find
  13. Tianrui Guan, Fuxiao Liu, Xiyang Wu, Ruiqi Xian, Zongxia Li, Xiaoyu Liu, Xijun Wang, Lichang Chen, Furong Huang, Yaser Yacoob, and 1 others. 2024b. Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models. In Proceedings of…
  14. Xudong Guo, Kaixuan Huang, Jiale Liu, Wenhui Fan, Natalia Vélez, Qingyun Wu, Huazheng Wang, Thomas L Griffiths, and Mengdi Wang. 2024. Embodied llm agents learn to cooperate in organized teams. arXiv preprint arXiv:2403.12482. — [arXiv:2403.12482](https://arxiv.org/abs/2403.12482) find
  15. Irene Huang, Wei Lin, Muhammad Jehanzeb Mirza, Jacob A Hansen, Sivan Doveh, Victor Ion Butoi, Roei Herzig, Assaf Arbelle, Hilde Kuehne, Trevor Darrell, Chuang Gan, Aude Oliva, Rogerio Feris, and Leonid Karlinsky. 2024a. Conme: Rethinking evaluation of compositional reasoning for modern VLMs. In The… find
  16. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and 1 others. 2025. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems,…
  17. Wen Huang, Hongbin Liu, Minxin Guo, and Neil Gong. 2024b. Visual hallucinations of multi-modal large language models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 9614– 9631, Bangkok, Thailand. Association for Computational Linguistics. find
  18. Yue Huang, Lichao Sun, Haoran Wang, Siyuan Wu, Qihui Zhang, Yuan Li, Chujie Gao, Yixin Huang, Wenhan Lyu, Yixuan Zhang, Xiner Li, Zhengliang Liu, Yixin Liu, Yijue Wang, Zhikun Zhang, Bertie Vidgen, Bhavya Kailkhura, Caiming Xiong, Chaowei Xiao, and 51 others. 2024c. Trustllm: Trustworthiness in larg…
  19. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276.
  20. Robin Jia and Percy Liang. 2017. Adversarial examples for evaluating reading comprehension systems. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2021–2031, Copenhagen, Denmark. Association for Computational Linguistics.
  21. Varun Khurana, Yaman Kumar Singla, Jayakumar Subramanian, Changyou Chen, Rajiv Ratn Shah, zhiqiang xu, and Balaji Krishnamurthy. 2025. Measuring and improving engagement of text-to-image generation models. In The Thirteenth International Conference on Learning Representations. find
  22. Jing Yu Koh, Robert Lo, Lawrence Jang, Vikram Duvvur, Ming Chong Lim, Po-Yu Huang, Graham Neubig, Shuyan Zhou, Ruslan Salakhutdinov, and Daniel Fried. 2024. Visualwebarena: Evaluating multimodal agents on realistic visual web tasks. arXiv preprint arXiv:2401.13649.
  23. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient memory management for large language model serving with pagedattention. In Proceedings of the 29th symposium on operating systems principles, pages 611–626.
  24. Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, and Chunyuan Li. 2025. LLaVA-onevision: Easy visual task transfer. Transactions on Machine Learning Research.
  25. Manling Li, Shiyu Zhao, Qineng Wang, Kangrui Wang, Yu Zhou, Sanjana Srivastava, Cem Gokmen, Tony Lee, Erran Li Li, Ruohan Zhang, and 1 others. 2024. Embodied agent interface: Benchmarking llms for embodied decision making. Advances in Neural Information Processing Systems, 37:100428–100534. find
  26. Kaizhao Liang, Lizhang Chen, Bo Liu, and Qiang Liu. 2024a. Cautious optimizers: Improving training with one line of code. arXiv preprint arXiv:2411.16085. — [arXiv:2411.16085](https://arxiv.org/abs/2411.16085) find
  27. Kaizhao Liang, Bo Liu, Lizhang Chen, and Qiang Liu. 2024b. Memory-efficient llm training with online subspace descent. Advances in Neural Information Processing Systems. find
  28. Daizong Liu, Mingyu Yang, Xiaoye Qu, Pan Zhou, Yu Cheng, and Wei Hu. 2024. A survey of attacks on large vision-language models: Resources, advances, and future trends. arXiv preprint arXiv:2407.07403. — [arXiv:2407.07403](https://arxiv.org/abs/2407.07403) find
  29. Fuxiao Liu, Kevin Lin, Linjie Li, Jianfeng Wang, Yaser Yacoob, and Lijuan Wang. 2023. Mitigating hallucination in large multi-modal models via robust instruction tuning. arXiv preprint arXiv:2306.14565.
  30. Jiale Liu, Yifan Zeng, Shaokun Zhang, Chi Zhang, Malte Højmark-Bertelsen, Marie Normann Gadeberg, Huazheng Wang, and Qingyun Wu. 2025. Divide, optimize, merge: Scalable fine-grained generative optimization for LLM agents. In Findings of the Association for Computational Linguistics: EMNLP 2025, page… find
  31. Ahmed Masry, Mohammed Saidul Islam, Mahir Ahmed, Aayush Bajaj, Firoz Kabir, Aaryaman Kartha, Md Tahmid Rahman Laskar, Mizanur Rahman, Shadikur Rahman, Mehrad Shahmohammadi, and 1 others. 2025. Chartqapro: A more diverse and challenging benchmark for chart question answering. arXiv preprint arXiv:250… find
  32. Llm-planner: Few-shot grounded planning for embodied agents with large language models. In Proceedings of the IEEE/CVF international conference on computer vision, pages 2998–3009.
  33. Son Nguyen, Lizhang Chen, Bo Liu, and Qiang Liu. 2024. H-fac: Memory-efficient optimization with factorized hamiltonian descent. International Conference on Artificial Intelligence and Statistics. find
  34. Linxin Song, Jiale Liu, Jieyu Zhang, Shaokun Zhang, Ao Luo, Shijian Wang, Qingyun Wu, and Chi Wang. 2024. Adaptive in-conversation team building for language model agents. arXiv preprint arXiv:2405.19425. — [arXiv:2405.19425](https://arxiv.org/abs/2405.19425) find
  35. OpenAI. 2023. GPT-4 technical report. https://cdn.openai.com/papers/GPT-4-Technical-Report. pdf. ↗
  36. Ethan Perez, Sam Ringer, Kamile Lukosiute, Karina Nguyen, Edwin Chen, Scott Heiner, Craig Pettit, Catherine Olsson, Sandipan Kundu, Saurav Kadavath, and 1 others. 2023. Discovering language model behaviors with model-written evaluations. In Findings of the association for computational linguistics:…
  37. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, and 1 others. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748–8…
  38. Christof Rapp. 2023. Aristotle’s Rhetoric. In Edward N. Zalta and Uri Nodelman, editors, The Stanford Encyclopedia of Philosophy, Winter 2023 edition. Metaphysics Research Lab, Stanford University. find
  39. Pritam Sarkar, Sayna Ebrahimi, Ali Etemad, Ahmad Beirami, Sercan O Arik, and Tomas Pfister. 2025. Mitigating object hallucination in MLLMs via data-augmented phrase-level alignment. In The Thirteenth International Conference on Learning Representations. find
  40. Rylan Schaeffer, Dan Valentine, Luke Bailey, James Chua, Cristobal Eyzaguirre, Zane Durante, Joe Benton, Brando Miranda, Henry Sleight, Tony Tong Wang, John Hughes, Rajashree Agrawal, Mrinank Sharma, Scott Emmons, Sanmi Koyejo, and Ethan Perez. 2025. Failures to find transferable image jailbreaks be… find
  41. Dustin Schwenk, Apoorv Khandelwal, Christopher Clark, Kenneth Marino, and Roozbeh Mottaghi. 2022. A-okvqa: A benchmark for visual question answering using world knowledge. Preprint, arXiv:2206.01718.
  42. Yan Shu, Hangui Lin, Yexin Liu, Yan Zhang, Gangyan Zeng, Yan Li, Yu Zhou, Ser-Nam Lim, Harry Yang, and Nicu Sebe. 2025. When semantics mislead vision: Mitigating large multimodal models hallucinations in scene text spotting and understanding. Preprint, arXiv:2506.05551. — [arXiv:2506.05551](https://arxiv.org/abs/2506.05551) find
  43. Chan Hee Song, Jiaman Wu, Clayton Washington, Brian M Sadler, Wei-Lun Chao, and Yu Su. 2023. find
  44. Sahar Tahmasebi, Eric Müller-Budack, and Ralph Ewerth. 2024. Multimodal misinformation detection using large vision-language models. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, pages 2189–2199. find
  45. Liyan Tang, Grace Kim, Xinyu Zhao, Thom Lake, Wenxuan Ding, Fangcong Yin, Prasann Singhal, Manya Wadhwa, Zeyu Leo Liu, Zayne Sprague, and 1 others. 2025a. Chartmuseum: Testing visual reasoning capabilities of large vision-language models. arXiv preprint arXiv:2505.13444. — [arXiv:2505.13444](https://arxiv.org/abs/2505.13444) find
  46. Liyan Tang, Shreyas Pimpalgaonkar, Kartik Sharma, Alexandros G. Dimakis, Maheswaran Sathiamoorthy, and Greg Durrett. 2025b. Bespoke-minichart-7b: pushing the frontiers of open vlms for chart understanding. https://www.bespokelabs.ai/blog/bespoke-minichart-7b. Accessed: 2025-04-23. ↗
  47. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, and 1 others. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805.
  48. Minh-Hao Van, Prateek Verma, and Xintao Wu. 2024. On large visual language models for medical imaging analysis: An empirical study. In 2024 IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), pages 172–176. IEEE. find
  49. Chenxi Wang, Xiang Chen, Ningyu Zhang, Bozhong Tian, Haoming Xu, Shumin Deng, and Huajun Chen. 2025a. MLLM can see? dynamic correction decoding for hallucination mitigation. In The Thirteenth International Conference on Learning Representations. find
  50. Haodi Wang, Kai Dong, Zhilei Zhu, Haotong Qin, Aishan Liu, Xiaolin Fang, Jiakai Wang, and Xianglong Liu. 2024a. Transferable multimodal attack on vision-language pre-training models. In 2024 IEEE Symposium on Security and Privacy (SP), pages 1722–1740. IEEE. find
  51. Xiaosen Wang, Shaokang Wang, Zhijin Ge, Yuyang Luo, and Shudong Zhang. 2025b. Attention! you vision language model could be maliciously manipulated. arXiv preprint arXiv:2505.19911. — [arXiv:2505.19911](https://arxiv.org/abs/2505.19911) find
  52. Yike Wang, Shangbin Feng, Heng Wang, Weijia Shi, Vidhisha Balachandran, Tianxing He, and Yulia Tsvetkov. 2024b. Resolving knowledge conflicts in large language models. In First Conference on Language Modeling.
  53. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. In International Conference on Learning Representations (ICLR).
  54. Junjie Wu, Yumeng Fu, Nan Yu, and Guohong Fu. 2025. E2lvlm: Evidence-enhanced large vision-language model for multimodal out-of-context misinformation detection. arXiv preprint arXiv:2502.10455. — [arXiv:2502.10455](https://arxiv.org/abs/2502.10455) find
  55. Zifan Ying, Qiusi Zhan, Zhixiang Liang, and Daniel Kang. 2024. Injecagent: Benchmarking indirect prompt injections in tool-integrated large language model agents. In Annual Meeting of the Association for Computational Linguistics.
  56. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, and 1 others. 2024. Autogen: Enabling next-gen llm applications via multi-agent conversations. In First Conference on Language Modeling. find
  57. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, and 1 others. 2025. The rise and potential of large language model based agents: A survey. Science China Information Sciences, 68(2):121101.
  58. Jian Xie, Kai Zhang, Jiangjie Chen, Renze Lou, and Yu Su. 2023. Adaptive chameleon or stubborn sloth: Revealing the behavior of large language models in knowledge conflicts. In The Twelfth International Conference on Learning Representations.
  59. Tinghao Xie, Xiangyu Qi, Yi Zeng, Yangsibo Huang, Udari Madhushani Sehwag, Kaixuan Huang, Luxi He, Boyi Wei, Dacheng Li, Ying Sheng, and 1 others. 2024. Sorry-bench: Systematically evaluating large language model safety refusal. arXiv preprint arXiv:2406.14598. find
  60. Rongwu Xu, Brian Lin, Shujian Yang, Tianqi Zhang, Weiyan Shi, Tianwei Zhang, Zhixuan Fang, Wei Xu, and Han Qiu. 2024. The earth is flat because...: Investigating LLMs’ belief towards misinformation via persuasive conversation. In Proceedings of the 62nd Annual Meeting of the Association for Computat… find
  61. Yuancheng Xu, Yanchao Sun, Micah Goldblum, Tom Goldstein, and Furong Huang. 2023. Exploring and exploiting decision boundary dynamics for adversarial robustness. In The Eleventh International Conference on Learning Representations. find
  62. Yi Zeng, Hongpeng Lin, Jingwen Zhang, Diyi Yang, Ruoxi Jia, and Weiyan Shi. 2024a. How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Lo…
  63. Yi Zeng, Hongpeng Lin, Jingwen Zhang, Diyi Yang, Ruoxi Jia, and Weiyan Shi. 2024b. How johnny can persuade LLMs to jailbreak them: Rethinking persuasion to challenge AI safety by humanizing LLMs. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Lo…
  64. Yifan Zeng, Yiran Wu, Xiao Zhang, Huazheng Wang, and Qingyun Wu. 2024c. Autodefense: Multi-agent llm defense against jailbreak attacks. arXiv preprint arXiv:2403.04783. — [arXiv:2403.04783](https://arxiv.org/abs/2403.04783) find
  65. Zaiwei Zhang, Gregory P. Meyer, Zhichao Lu, Ashish Shrivastava, Avinash Ravichandran, and Eric M. Wolff. 2024. Vlm-kd: Knowledge distillation from vlm for long-tail visual recognition. Preprint, arXiv:2408.16930. — [arXiv:2408.16930](https://arxiv.org/abs/2408.16930) find
  66. Yunqing Zhao, Tianyu Pang, Chao Du, Xiao Yang, Chongxuan Li, Ngai-Man Man Cheung, and Min Lin. 2023. On evaluating adversarial robustness of large vision-language models. Advances in Neural Information Processing Systems, 36:54111–54138. find
  67. Boyuan Zheng, Boyu Gou, Jihyung Kil, Huan Sun, and Yu Su. 2024. Gpt-4v (ision) is a generalist web agent, if grounded. arXiv preprint arXiv:2401.01614.
  68. Shiyu Xuan, Ming Yang, and Shiliang Zhang. 2024. Adapting vision-language models via learning to inject knowledge. IEEE Transactions on Image Processing. find
  69. Weihong Zhong, Xiaocheng Feng, Liang Zhao, Qiming Li, Lei Huang, Yuxuan Gu, Weitao Ma, Yuan Xu, and Bing Qin. 2024. Investigating and mitigating the multimodal hallucination snowballing in large vision-language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Li… find
  70. Tianyun Yang, Ziniu Li, Juan Cao, and Chang Xu. 2025. Mitigating hallucination in large vision-language models via modular attribution and intervention. In The Thirteenth International Conference on Learning Representations. find
  71. Wanqi Zhou, Shuanghao Bai, Danilo P Mandic, Qibin Zhao, and Badong Chen. 2024a. Revisiting the adversarial robustness of vision language models: a multimodal perspective. arXiv preprint arXiv:2404.19287. — [arXiv:2404.19287](https://arxiv.org/abs/2404.19287) find
  72. Xingcheng Zhou, Mingyu Liu, Ekim Yurtsever, Bare Luka Zagar, Walter Zimmer, Hu Cao, and Alois C Knoll. 2024b. Vision language models in autonomous driving: A survey and outlook. IEEE Transactions on Intelligent Vehicles. find
  73. Yiwei Zhou, Xiaobo Xia, Zhiwei Lin, Bo Han, and Tongliang Liu. 2024c. Few-shot adversarial prompt learning on vision-language models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. find
  74. Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J Zico Kolter, and Matt Fredrikson. 2023. Universal and transferable adversarial attacks on aligned language models. arXiv preprint arXiv:2307.15043.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2026-do-images-speak-louder-than/