Elamur Research⌕
☰
home / papers / 2026 / Dialectical Structured Reasoning for Explainable Multimodal Fake News Detection

Dialectical Structured Reasoning for Explainable Multimodal Fake News Detection

Paper · 2026 · Ruichao Yang, Yufan Bian, Wei Gao et al.

Summary

The paper addresses multimodal fake news detection, where most existing detectors fuse text and image features into a single vector. Such classifiers give little insight into how they weigh contradictory evidence spread across fragmented, polarized social media threads. The authors propose Dialectical Structured Reasoning (DSR), which treats verification as a structured argument. For each news item, they build a heterogeneous propagation graph with news, post, user, image and topic nodes. Two MLLM-guided agents then traverse this graph under opposite hypotheses. The Verifier collects paths that support consistency, while the Debunker searches for factual or logical conflicts. A trainable, differentiable Judge agent weighs these competing paths using path-based attention and Background Knowledge Injection (BKI) drawn from the MLLM's parametric knowledge. It then outputs a label and a natural-language explanation. On three benchmarks, DSR reportedly beats unimodal, multimodal and social-context baselines. A user study suggests its explanations help people judge veracity more accurately and confidently. This matters because it moves explainability from post-hoc rationales into the decision process itself.

Key points

  • Path mining: Node importance is scored with PageRank. A beam search, steered by an MLLM such as GPT-5, extracts hypothesis-conditioned evidence paths for H_real and H_fake.
  • Differences from debate-based methods such as TED: The Judge is differentiable and fine-tuned with LoRA, so the system can be optimized end to end instead of relying only on prompting.
  • Cost:
    • Offline traversal and BKI take about 9–14 s per instance and can be cached. This compares with roughly 25 s for RPPG-Fake.
    • Online Judge inference takes under 0.1 s.
  • Robustness and reproducibility:
    • Main experiments use proprietary APIs (GPT-5, Gemini-3), but the pipeline also runs with open models such as Qwen2-VL-7B.
    • Accuracy varies by less than 0.8% across equivalent prompt variants.
  • Human evaluation and limitations:
    • In a study with 6 participants, DSR outputs led to more accurate veracity judgments and higher confidence than RPPG-Fake outputs.
    • The method does not target pixel-level image manipulation.

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

🎓Singapore Management UniversitySingapore · Singapore35 works · 2,457 citations🎓Hong Kong Baptist UniversityHong Kong · China10 works · 246 citations🎓University of Science and Technology BeijingBeijing · China10 works · 315 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksComputer Vision and Pattern Recognition · 3,486 worksSocial Sciences · 1,954 worksInformation Systems · 1,730 worksSociology and Political Science · 626 works

🧭 Topics 2Research subjects and languages the work is about.Reasoning · 1,685 worksVision & language · 811 works

Cite

Cite as Ruichao Yang, Yufan Bian, Wei Gao, Bo-Wen Zhang, Jing Ma, Hongzhan Lin, Ziyang Luo, Xiaobin Zhu and Xu-Cheng Yin. 2026. Dialectical Structured Reasoning for Explainable Multimodal Fake News Detection. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.1601

@inproceedings{yang2026dialectical,
  title = {{Dialectical Structured Reasoning for Explainable Multimodal Fake News Detection}},
  author = {Ruichao Yang, Yufan Bian, Wei Gao, Bo-Wen Zhang, Jing Ma, Hongzhan Lin, Ziyang Luo, Xiaobin Zhu and Xu-Cheng Yin},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1601},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1601}
}

References

57 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Tian Bian, Xi Xiao, Tingyang Xu, Peilin Zhao, Wenbing Huang, Yu Rong, and Junzhou Huang. 2020. Rumor detection on social media with bi-directional graph convolutional networks. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 549–556. find
  2. David M Blei, Andrew Y Ng, and Michael I Jordan. 2003. Latent dirichlet allocation. the Journal of machine Learning research, 3:993–1022.
  3. Sergey Brin and Lawrence Page. 1998. The anatomy of a large-scale hypertextual web search engine. Computer networks and ISDN systems, 30(1-7):107–117.
  4. Yixuan Chen, Dongsheng Li, Peng Zhang, Jie Sui, Qin Lv, Lu Tun, and Li Shang. 2022. Cross-modal ambiguity learning for multimodal fake news detection. find
  5. In Proceedings of the ACM web conference 2022, pages 2897–2905. find
  6. Google. 2025. Build with our next generation ai systems. find
  7. Chen Han, Wenzhen Zheng, and Xijin Tang. 2025. Debate-to-detect: Reformulating misinformation detection as a real-world debate with large language models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 15125–15140, Suzhou, China. Association for Comp… find
  8. Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, and 1 others. 2021. Lora: Low-rank adaptation of large language models. In International Conference on Learning Representations.
  9. Runsheng Huang, Liam Dugan, Yue Yang, and Chris Callison-Burch. 2024. MiRAGeNews: Multimodal realistic AI-generated news detection. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16436–16448, Miami, Florida, USA. Association for Computational Linguistics. find
  10. Jing Jing, Hongchen Wu, Jie Sun, Xiaochang Fang, and Huaxiang Zhang. 2023. Multimodal fake news detection via progressive fusion networks. Information processing & management, 60(1):103120. find
  11. Ankur Joshi, Saket Kale, Satish Chandel, and D Kumar Pal. 2015. Likert scale: Explored and explained. British journal of applied science & technology, 7(4):396. find
  12. Dhruv Khattar, Jaipal Singh Goud, Manish Gupta, and Vasudeva Varma. 2019. Mvae: Multimodal variational autoencoder for fake news detection. In The world wide web conference, pages 2915–2921. find
  13. Huy Hoan Le, Van Sy Thinh Nguyen, Thi Le Chi Dang, Vo Thanh Khang Nguyen, Truong Thanh Hung Nguyen, and Hung Cao. 2025. Multimedia verification through multi-agent deep research multimodal large language models. In Proceedings of the 33rd ACM International Conference on Multimedia, pages 14034–14040… find
  14. Hui Li, Ante Wang, Kunquan Li, Zhihao Wang, Liang Zhang, Delai Qiu, Qingsong Liu, and Jinsong Su. 2025a. A multi-agent framework with automated decision rule optimization for cross-domain misinformation detection. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Process… find
  15. Jun Li, Yi Bin, Liang Peng, Yang Yang, Yangyang Li, Hao Jin, and Zi Huang. 2024. Focusing on relevant responses for multi-modal rumor detection. IEEE Transactions on Knowledge and Data Engineering, 36(11):6225–6236. find
  16. Mingxin Li, Yuchen Zhang, Haowei Xu, Xianghua Li, Chao Gao, and Zhen Wang. 2025b. Learning complex heterogeneous multimodal fake news via social latent network inference. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 433–441. find
  17. Hongzhan Lin, Zixin Chen, Zhiqi Shen, Ziyang Luo, Zhen Ye, Jing Ma, Tat-Seng Chua, and Guandong Xu. 2026. Towards comprehensive stage-wise benchmarking of large language models in fact-checking. arXiv preprint arXiv:2601.02669. — [arXiv:2601.02669](https://arxiv.org/abs/2601.02669) find
  18. Yifan Liu, Yaokun Liu, Zelin Li, Ruichen Yao, Yang Zhang, and Dong Wang. 2025a. Modality interactive mixture-of-experts for fake news detection. In Proceedings of the ACM on Web Conference 2025, pages 5139–5150. find
  19. 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.
  20. Yuhan Liu, Yuxuan Liu, Xiaoqing Zhang, Xiuying Chen, and Rui Yan. 2025b. The truth becomes clearer through debate! multi-agent systems with large language models unmask fake news. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, page… find
  21. Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization. In International Conference on Learning Representations. find
  22. Weihai Lu, Yu Tong, and Zhiqiu Ye. 2025. Dammfnd: Domain-aware multimodal multi-view fake news detection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 559– 567. find
  23. Yi-Ju Lu and Cheng-Te Li. 2020. Gcan: Graph-aware co-attention networks for explainable fake news detection on social media. In ACL.
  24. Jing Ma, Wei Gao, Prasenjit Mitra, Sejeong Kwon, Bernard J Jansen, Kam-Fai Wong, and Meeyoung Cha. 2016. Detecting rumors from microblogs with recurrent neural networks. In IJCAI. find
  25. Hugo Mercier and Dan Sperber. 2017. The enigma of reason. Harvard University Press. find
  26. Meta. 2025. Llama 4: Leading intelligence. unrivaled speed and efficiency. find
  27. Kai Nakamura, Sharon Levy, and William Yang Wang. 2020. Fakeddit: A new multimodal benchmark dataset for fine-grained fake news detection. In Proceedings of the twelfth language resources and evaluation conference, pages 6149–6157. find
  28. Raymond S Nickerson. 1998. Confirmation bias: A ubiquitous phenomenon in many guises. Review of general psychology, 2(2):175–220. find
  29. OpenAI. 2025. Gpt-5 system card. find
  30. Hui Pang, Chaozhuo Li, Litian Zhang, Senzhang Wang, and Xi Zhang. 2025. Beyond text: Fine-grained multi-modal fact verification with hypergraph transformers. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 6389–6397. find
  31. Peng Qi, Juan Cao, Xirong Li, Huan Liu, Qiang Sheng, Xiaoyue Mi, Qin He, Yongbiao Lv, Chenyang Guo, and Yingchao Yu. 2021. Improving fake news detection by using an entity-enhanced framework to fuse diverse multimodal clues. In Proceedings of the 29th ACM international conference on multimedia, page… find
  32. Peng Qi, Zehong Yan, Wynne Hsu, and Mong Li Lee. 2024. Sniffer: Multimodal large language model for explainable out-of-context misinformation detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13052–13062. find
  33. Kai Shu, Deepak Mahudeswaran, Suhang Wang, Dongwon Lee, and Huan Liu. 2020. Fakenewsnet: A data repository with news content, social context, and spatiotemporal information for studying fake news on social media. Big data, 8(3):171–188. find
  34. Shivangi Singhal, Tanisha Pandey, Saksham Mrig, Rajiv Ratn Shah, and Ponnurangam Kumaraguru. 2022. Leveraging intra and inter modality relationship for multimodal fake news detection. In Companion proceedings of the Web conference 2022, pages 726–734. find
  35. Xinqi Su, Zitong Yu, Yawen Cui, Ajian Liu, Xun Lin, Yuhao Wang, Haochen Liang, Wenhui Li, Li Shen, and Xiaochun Cao. 2025. Dynamic analysis and adaptive discriminator for fake news detection. In Proceedings of the 33rd ACM International Conference on Multimedia, pages 8164–8173. find
  36. 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
  37. Yu Tong, Weihai Lu, Xiaoxi Cui, Yifan Mao, and Zhejun Zhao. 2025. Dapt: Domain-aware prompt-tuning for multimodal fake news detection. In Proceedings of the 33rd ACM International Conference on Multimedia, pages 7902–7911. find
  38. Yu Tong, Weihai Lu, Zhe Zhao, Song Lai, and Tong Shi. 2024. Mmdfnd: Multi-modal multi-domain fake news detection. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 1178–1186. find
  39. Pat Verga, Haitian Sun, Livio Baldini Soares, and William Cohen. 2021. Adaptable and interpretable neural MemoryOver symbolic knowledge. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3678–3691,… find
  40. Ashwin Vijayakumar, Michael Cogswell, Ramprasaath Selvaraju, Qing Sun, Stefan Lee, David Crandall, and Dhruv Batra. 2018. Diverse beam search for improved description of complex scenes. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32. find
  41. Bo Wang, Jing Ma, Hongzhan Lin, Zhiwei Yang, Ruichao Yang, Yuan Tian, and Yi Chang. 2024a. Explainable fake news detection with large language model via defense among competing wisdom. In Proceedings of the ACM Web Conference 2024, pages 2452–2463. find
  42. Jiandong Wang, Hongguang Zhang, Chun Liu, and Xiongjun Yang. 2024b. Fake news detection via multi-scale semantic alignment and cross-modal attention. In Proceedings of the 47th international ACM SIGIR conference on research and development in information retrieval, pages 2406–2410. find
  43. Yaqing Wang, Fenglong Ma, Zhiwei Jin, Ye Yuan, Guangxu Xun, Kishlay Jha, Lu Su, and Jing Gao. 2018. Eann: Event adversarial neural networks for multi-modal fake news detection. In Proceedings of the 24th acm sigkdd international conference on knowledge discovery & data mining, pages 849– 857. find
  44. Lianwei Wu, Pusheng Liu, Yongqiang Zhao, Peng Wang, and Yangning Zhang. 2023. Human cognition-based consistency inference networks for multi-modal fake news detection. IEEE Transactions on Knowledge and Data Engineering, 36(1):211–225. find
  45. Yang Wu, Pengwei Zhan, Yunjian Zhang, Liming Wang, and Zhen Xu. 2021. Multimodal fusion with co-attention networks for fake news detection. In Findings of the association for computational linguistics: ACL-IJCNLP 2021, pages 2560–2569. find
  46. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, and 23 others. 2025. Qwen2.5 technical report. Preprint, arXiv:241… find
  47. Zhiwei Yang, Jing Ma, Hechang Chen, Hongzhan Lin, Ziyang Luo, and Yi Chang. 2022. A coarse-to-fine cascaded evidence-distillation neural network for explainable fake news detection. In Proceedings of the 29th international conference on computational linguistics, pages 2608–2621. find
  48. Qichao Ying, Xiaoxiao Hu, Yangming Zhou, Zhenxing Qian, Dan Zeng, and Shiming Ge. 2023. Bootstrapping multi-view representations for fake news detection. In Proceedings of the AAAI conference on Artificial Intelligence, volume 37, pages 5384–5392. find
  49. Zhi Zeng, Mingmin Wu, Guodong Li, Xiang Li, Zhongqiang Huang, and Ying Sha. 2023. An Explainable Multi-view Semantic Fusion Model for Multimodal Fake News Detection . In 2023 IEEE International Conference on Multimedia and Expo (ICME), pages 1235–1240, Los Alamitos, CA, USA. IEEE Computer Society. find
  50. Fanrui Zhang, Jiawei Liu, Jingyi Xie, Qiang Zhang, Yongchao Xu, and Zheng-Jun Zha. 2024a. Escnet: Entity-enhanced and stance checking network for multi-modal fact-checking. In Proceedings of the ACM Web Conference 2024, pages 2429–2440. find
  51. Litian Zhang, Xiaoming Zhang, Ziyi Zhou, Xi Zhang, Senzhang Wang, Philip S Yu, and Chaozhuo Li. 2024b. Early detection of multimodal fake news via reinforced propagation path generation. IEEE Transactions on Knowledge and Data Engineering. find
  52. Tianlin Zhang, En Yu, Yi Shao, and Jiande Sun. 2025. Multimodal inverse attention network with intrinsic discriminant feature exploitation for fake news detection. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25, pages 7940–7948. International… find
  53. Yangming Zhou, Yuzhou Yang, Qichao Ying, Zhenxing Qian, and Xinpeng Zhang. 2023. Multimodal fake news detection via clip-guided learning. In 2023 IEEE international conference on multimedia and expo (ICME), pages 2825–2830. IEEE. find
  54. Peican Zhu, Yubo Jing, Le Cheng, Keke Tang, and Yangming Guo. 2025a. Ken: Knowledge augmentation and emotion guidance network for multimodal fake news detection. In Proceedings of the 33rd ACM International Conference on Multimedia, pages 1793–1801. find
  55. Ye Zhu, Yunan Wang, and Zitong Yu. 2025b. Multimodal fake news detection: Mfnd dataset and shallow-deep multitask learning. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25, pages 8012–8020. International Joint Conferences on Artificial Intellig… find
  56. Fabiana Zollo, Alessandro Bessi, Michela Del Vicario, Antonio Scala, Guido Caldarelli, Louis Shekhtman, Shlomo Havlin, and Walter Quattrociocchi. 2017. Debunking in a world of tribes. PloS one, 12(7):e0181821. find
  57. Frederik J Zuiderveen Borgesius, Damian Trilling, Judith Möller, Balázs Bodó, Claes H De Vreese, and Natali Helberger. 2016. Should we worry about filter bubbles? Internet policy review, 5(1). find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/yang-2026-dialectical-structured-reasoning-explainable-multimodal/