Elamur Research⌕
☰
home / papers / 2026 / From Form to Logic: Masked Reconstruction and Reasoning Distillation for Short Video Fake News Detection

From Form to Logic: Masked Reconstruction and Reasoning Distillation for Short Video Fake News Detection

Paper · 2026 · Qingyan Wang, Lianwei Wu, Botao Wang et al.

Summary

The paper addresses automatic detection of fake news in short videos from platforms like TikTok, where vision, audio and text combine. The authors identify two weaknesses in existing detectors. Models that match modalities globally overlook small local contradictions. LLM-based detectors catch implausible narratives but hallucinate and run slowly. They propose PCDD (Perception-Cognition Dual-driven Detector), which has two branches:

  • Perceptual Clue Discovery (PCD): masks the tail of one modality at a time and reconstructs it from the others using Qwen2.5-Omni-3B features. Large reconstruction residuals then reveal cross-modal conflicts.
  • Cognitive Logic Reasoning (CLR): uses Regularity–Relation–Result (R³) distillation to transfer an LLM teacher's reasoning chain to a small student model. The chain covers evidence screening, relation building and the final verdict.

A gated adaptive fusion merges both signals. Because no LLM runs at inference time, the system is faster and avoids generative hallucination. On FakeSV and FakeTT, PCDD beats prior baselines, offers interpretable evidence and stays robust with little training data. This makes it a practical aid for human fact-checkers.

Key points

  • Inputs: video title, on-screen text, audio transcript, keyframes and the audio signal. The three text fields are concatenated, and the task is framed as binary real/fake classification.
  • Efficiency: at 3B parameters, PCDD is the smallest of the MLLM-based systems compared. It averages 0.92 s per sample on an NVIDIA RTX 4090, versus tens of seconds for generative MLLMs.
  • Teacher robustness: results stay stable across four teachers (DeepSeek-R1, Qwen3, GLM4.7 and GPT5).
  • Hyperparameters and low-data results: using the first f = 8 backbone layers works best. With only 1–30% of the training data, PCDD mostly outperforms SVFEND and FakingRecipe.
  • Code: available at github.com/SeinCore/PCDD. The authors note that highly consistent, sophisticated forgeries and long, complex videos remain difficult.

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

🎓Hefei University of TechnologyHefei · China10 works · 1,615 citations🎓Northwestern Polytechnical UniversityXi'an · China13 works · 67 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksComputer Vision and Pattern Recognition · 2,869 worksSocial Sciences · 1,772 worksSociology and Political Science · 577 works

🧭 Topics 2Research subjects and languages the work is about.Reasoning · 1,426 worksEfficient models & compression · 242 works

Cite

Cite as Qingyan Wang, Lianwei Wu, Botao Wang, Wangkang and Yaxiong Wang. 2026. From Form to Logic: Masked Reconstruction and Reasoning Distillation for Short Video Fake News Detection. Proceedings of the 64th Annual Meeting 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.acl-long.579

@inproceedings{wang2026form,
  title = {{From Form to Logic: Masked Reconstruction and Reasoning Distillation for Short Video Fake News Detection}},
  author = {Qingyan Wang, Lianwei Wu, Botao Wang, Wangkang and Yaxiong Wang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.579},
  url = {https://doi.org/10.18653/v1/2026.acl-long.579}
}

References

43 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Marcella Astrid, Enjie Ghorbel, and Djamila Aouada. 2025. Audio-visual deepfake detection with local temporal inconsistencies. In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5. IEEE. find
  2. Shuai Bai, Yuxuan Cai, Ruizhe Chen, Keqin Chen, Xionghui Chen, Zesen Cheng, Lianghao Deng, Wei Ding, Chang Gao, Chunjiang Ge, Wenbin Ge, Zhifang Guo, Qidong Huang, Jie Huang, Fei Huang, Binyuan Hui, Shutong Jiang, Zhaohai Li, Mingsheng Li, and 45 others. 2025. Qwen3-vl technical report. Preprint, ar…
  3. Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is space-time attention all you need for video understanding? In ICML, volume 2, page 4. find
  4. Yuyan Bu, Qiang Sheng, Juan Cao, Peng Qi, Danding Wang, and Jintao Li. 2023. Combating online misinformation videos: Characterization, detection, and future directions. In Proceedings of the 31st ACM International Conference on Multimedia, pages 8770–8780. find
  5. Yuyan Bu, Qiang Sheng, Juan Cao, Peng Qi, Danding Wang, and Jintao Li. 2024. Fakingrecipe: Detecting fake news on short video platforms from the perspective of creative process. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 1351–1360. find
  6. 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. In Proceedings of the ACM web conference 2022, pages 2897–2905. find
  7. Hyewon Choi and Youngjoong Ko. 2021. Using topic modeling and adversarial neural networks for fake news video detection. In Proceedings of the 30th ACM international conference on information & knowledge management, pages 2950–2954. find
  8. Rui Hou, Verónica Pérez-Rosas, Stacy Loeb, and Rada Mihalcea. 2019. Towards automatic detection of misinformation in online medical videos. In 2019 International conference on multimodal interaction, pages 235–243. find
  9. Steven Davis and Paul Mermelstein. 1980. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE transactions on acoustics, speech, and signal processing, 28(4):357–366. find
  10. Aaron Hurst, Adam Lerer, Adam P. Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, Aleksander M adry, Alex Baker-Whitcomb, Alex Beutel, Alex Borzunov, Alex Carney, Alex Chow, Alex Kirillov, Alex Nichol, Alex Paino, and 399 others. 2024. Gpt-4o…
  11. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies,…
  12. Alexey Dosovitskiy. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.
  13. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, and 175 others. 2025. Deepseek-r1 incentivizes reasoning in llms through rein… find
  14. Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, and Ross Girshick. 2022. Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16000–16009.
  15. Shawn Hershey, Sourish Chaudhuri, Daniel P. W. Ellis, Jort F. Gemmeke, Aren Jansen, R. Channing Moore, Manoj Plakal, Devin Platt, Rif A. Saurous, Bryan Seybold, Malcolm Slaney, Ron J. Weiss, and Kevin Wilson. 2017. Cnn architectures for large-scale audio classification. In 2017 ieee international co… find
  16. Yuhan Liu, Zirui Song, Juntian Zhang, Xiaoqing Zhang, Xiuying Chen, and Rui Yan. 2025. The stepwise deception: Simulating the evolution from true news to fake news with llm agents. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 26187–26203.
  17. Olga Papadopoulou, Markos Zampoglou, Symeon Papadopoulos, and Yiannis Kompatsiaris. 2017. Web video verification using contextual cues. In Proceedings of the 2nd international workshop on multimedia forensics and security, pages 6–10. find
  18. Wonpyo Park, Dongju Kim, Yan Lu, and Minsu Cho. 2019. Relational knowledge distillation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 3967–3976. find
  19. Liwen Peng, Songlei Jian, Zhigang Kan, Linbo Qiao, and Dongsheng Li. 2024. Not all fake news is semantically similar: Contextual semantic representation learning for multimodal fake news detection. Information Processing & Management, 61(1):103564. find
  20. Gordon Pennycook and David G Rand. 2021. The psychology of fake news. Trends in cognitive sciences, 25(5):388–402. find
  21. Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531.
  22. Peng Qi, Yuyan Bu, Juan Cao, Wei Ji, Ruihao Shui, Junbin Xiao, Danding Wang, and Tat-Seng Chua. 2023. Fakesv: A multimodal benchmark with rich social context for fake news detection on short video platforms. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 14444– 14… find
  23. Rongpei Hong, Jian Lang, Jin Xu, Zhangtao Cheng, Ting Zhong, and Fan Zhou. 2025a. Following clues, approaching the truth: Explainable micro-video rumor detection via chain-of-thought reasoning. In Proceedings of the ACM on Web Conference 2025, pages 4684–4698. find
  24. Shengsheng Qian, Jinguang Wang, Jun Hu, Quan Fang, and Changsheng Xu. 2021. Hierarchical multi-modal contextual attention network for fake news detection. In Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval, pages 153–162. find
  25. Wenyi Hong, Wenmeng Yu, Xiaotao Gu, Guo Wang, Guobing Gan, Haomiao Tang, Jiale Cheng, Ji Qi, Junhui Ji, Lihang Pan, Shuaiqi Duan, Weihan Wang, Yan Wang, Yean Cheng, Zehai He, Zhe Su, Zhen Yang, Ziyang Pan, Aohan Zeng, and 68 others. 2025b. Glm-4.5v and glm-4.1v-thinking: Towards versatile multimodal…
  26. Juan Carlos Medina Serrano, Orestis Papakyriakopoulos, and Simon Hegelich. 2020. Nlp-based feature extraction for the detection of covid-19 misinformation videos on youtube. In Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020. find
  27. Lanyu Shang, Ziyi Kou, Yang Zhang, and Dong Wang. 2021. A multimodal misinformation detector for covid-19 short videos on tiktok. In 2021 IEEE international conference on big data (big data), pages 899–908. IEEE. find
  28. Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388.
  29. Aaditya Singh, Adam Fry, Adam Perelman, Adam Tart, Adi Ganesh, Ahmed El-Kishky, Aidan McLaughlin, Aiden Low, AJ Ostrow, Akhila Ananthram, Akshay Nathan, Alan Luo, Alec Helyar, Aleksander Madry, Aleksandr Efremov, Aleksandra Spyra, Alex Baker-Whitcomb, Alex Beutel, Alex Karpenko, and 465 others. 2025… — OpenAI GPT-5 System Card
  30. Sergey Zagoruyko and Nikos Komodakis. 2016. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928. find
  31. Mason Walker and Katerina Eva Matsa. 2021. News consumption across social media in 2021: more than half of twitter users get news on the site regularly. pew research center. find
  32. Qingyan Wang, Lianwei Wu, Yuanxia Zeng, Linyong Wang, Kang Wang, Yaxiong Wang, and Chao Gao. 2025. Cross-modal consistency reasoning with large language models for short video-based fake news detection. In Proceedings of the 2nd International Workshop on Diffusion of Harmful Content on Online Web, p… find
  33. Shuting Wang, Min-Seok Pang, and Paul A Pavlou. 2022. Seeing is believing? how including a video in fake news influences users’ reporting of fake news to social media platforms. MIS quarterly, 46(3):1323– 1354. find
  34. Lianwei Wu, Pusheng Liu, and Yanning Zhang. 2023a. See how you read? multi-reading habits fusion reasoning for multi-modal fake news detection. In Proceedings of the AAAI conference on artificial intelligence, volume 37, pages 13736–13744. find
  35. Lianwei Wu, Pusheng Liu, Yongqiang Zhao, Peng Wang, and Yangning Zhang. 2023b. Human cognition-based consistency inference networks for multi-modal fake news detection. IEEE Transactions on Knowledge and Data Engineering, 36(1):211– 225. find
  36. Lianwei Wu, Yuzhou Long, Chao Gao, Zhen Wang, and Yanning Zhang. 2023c. Mfir: Multimodal fusion and inconsistency reasoning for explainable fake news detection. Information Fusion, 100:101944. find
  37. Peihao Xiang, Chaohao Lin, Kaida Wu, and Ou Bai. 2024. Multimae-der: Multimodal masked autoencoder for dynamic emotion recognition. In 2024 14th International Conference on Pattern Recognition Systems (ICPRS), pages 1–7. IEEE. find
  38. Jin Xu, Zhifang Guo, Jinzheng He, Hangrui Hu, Ting He, Shuai Bai, Keqin Chen, Jialin Wang, Yang Fan, Kai Dang, Bin Zhang, Xiong Wang, Yunfei Chu, and Junyang Lin. 2025. Qwen2.5-omni technical report. arXiv preprint arXiv:2503.20215.
  39. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Aohan Zeng, Xin Lv, Qinkai Zheng, Zhenyu Hou, Bin Chen, Chengxing Xie, Cunxiang Wang, Da Yin, Hao Zeng, Jiajie Zhan… — GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
  40. Zhi Zeng, Minnan Luo, Xiangzheng Kong, Huan Liu, Hao Guo, Hao Yang, Zihan Ma, and Xiang Zhao. 2024. Mitigating world biases: A multimodal multi-view debiasing framework for fake news video detection. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 6492–6500. find
  41. Fanrui Zhang, Dian Li, Qiang Zhang, Jun Chen, Gang Liu, Junxiong Lin, Jiahong Yan, Jiawei Liu, and Zheng-Jun Zha. 2025a. Fact-r1: Towards explainable video misinformation detection with deep reasoning. arXiv preprint arXiv:2505.16836. — [arXiv:2505.16836](https://arxiv.org/abs/2505.16836) find
  42. Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, Fei Huang, and Jingren Zhou. 2025b. Qwen3 embedding: Advancing text embedding and reranking through foundation models. Preprint, arXiv:2506.05176.
  43. Linlin Zong, Jiahui Zhou, Wenmin Lin, Xinyue Liu, Xianchao Zhang, and Bo Xu. 2024. Unveiling opinion evolution via prompting and diffusion for short video fake news detection. In Findings of the Association for Computational Linguistics ACL 2024, pages 10817–10826. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2026-form-logic-masked-reconstruction-reasoning/