Elamur Research⌕
☰
home / papers / 2025 / The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents

The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents

Paper · 2025 · Yuhan Liu, Zirui Song, Juntian Zhang et al.

Summary

Most misinformation research treats fake news as something already present in a network and studies how it spreads or how to detect it. This paper examines an earlier stage: how an accurate report gradually becomes false as people retell it. The authors present FUSE, a simulation in which LLM-driven agents with personas live in high-clustering, scale-free or random social networks. Each agent has one of four roles: spreader, commentator, verifier or bystander. Every simulated day, agents swap versions of a story and rewrite it, drawing on both short-term and long-term memory. A companion scoring scheme, FUSE-EVAL, uses an LLM to rate how far each version has drifted from the original along six dimensions.

The simulations reproduce several patterns reported in earlier studies. Distortion builds up over time, and it happens faster in high-clustering networks and in political news. Bringing in an official agent to correct the story early, and again later, clearly reduces the drift. This gives a controllable testbed for studying early-stage interventions against misinformation.

Key points

  • FUSE-EVAL measures drift along six axes: changes in sentiment (SS), the addition of new information (NII), changes in certainty (CS), changes in style (STS), changes in temporal framing (TS) and deviation in perspective (PD).
  • PD contributes most to the evolution of fake news (22.3%), followed by NII (18%), STS (17.5%) and SS (17.2%); TS contributes least (11%).
  • An official agent placed at high-degree nodes was tested as an intervention:
    • A correction at the day-6 peak cut deviation by 37.8% versus no intervention.
    • A second correction on day 16 cut it by 31.8%.
    • Overall, final deviation fell 28.6% and deviation variance fell 61.8%.
  • Topic matters:
    • Political news drifts faster than terrorism, disaster, science and finance stories.
    • Science stories change mainly through new information rather than stylistic or temporal shifts.
  • The authors list three limitations:
    • No datasets yet capture the true-to-false transition.
    • Broader factors such as political agendas or ideological bias are not modeled.
    • Relying on LLMs for both simulation and evaluation may introduce bias.

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

🎓Renmin University of ChinaBeijing · China114 works · 16,118 citations🎓Mohamed bin Zayed University of Artificial IntelligenceAbu Dhabi · United Arab Emirates124 works · 5,676 citations🎓Wuhan UniversityWuhan · China35 works · 1,127 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksSocial Sciences · 1,772 worksInformation Systems · 1,437 worksSociology and Political Science · 577 worksPhysics and Astronomy · 44 worksStatistical and Nonlinear Physics · 40 works

Cite

Cite as 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. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.emnlp-main.1330

@inproceedings{liu2025stepwise,
  title = {{The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents}},
  author = {Yuhan Liu, Zirui Song, Juntian Zhang, Xiaoqing Zhang, Xiuying Chen and Rui Yan},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  year = {2025},
  doi = {10.18653/v1/2025.emnlp-main.1330},
  url = {https://doi.org/10.18653/v1/2025.emnlp-main.1330}
}

References

48 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Murray R Barrick and Michael K Mount. 1991. The big five personality dimensions and job performance: a meta-analysis. Personnel Psychology, 44(1):1–26. find
  2. Xiuying Chen, Mingzhe Li, Shen Gao, Xin Cheng, Qiang Yang, Qishen Zhang, Xin Gao, and Xiangliang Zhang. 2023a. A topic-aware summarization framework with different modal side information. In SI-GIR ’23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Informa… find
  3. Xiuying Chen, Guodong Long, Chongyang Tao, Mingzhe Li, Xin Gao, Chengqi Zhang, and Xiangliang Zhang. 2023b. Improving the robustness of summarization systems with dual augmentation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pa… find
  4. Matteo Cinelli, Gianmarco De Francisci Morales, Alessandro Galeazzi, Walter Quattrociocchi, and Michele Starnini. 2021. The echo chamber effect on social media. Proceedings of the National Academy of Sciences, 118(9):e2023301118. find
  5. Patrick Oliveira de Paula, Alejandra Rada, and Catalina Rúa. 2024. Application of information theory in rumor spreading modeling considering polarization in complex networks. Preprint, arXiv:2408.08891. — [arXiv:2408.08891](https://arxiv.org/abs/2408.08891) find
  6. Kiran Garimella, Aristides Gionis, Nikos Parotsidis, and Nikolaj Tatti. 2017. Balancing information exposure in social networks. Advances in Neural Information Processing Systems, 30. find
  7. Mingfei Guo, Xiuying Chen, Juntao Li, Dongyan Zhao, and Rui Yan. 2021. How does truth evolve into fake news? an empirical study of fake news evolution. In Companion Proceedings of the Web Conference 2021, pages 407–411. ACM. find
  8. Mahdi Jalili and Matjaž Perc. 2017. Information cascades in complex networks. Journal of Complex Networks, 5(5):665–693. find
  9. Song Jin, Juntian Zhang, Yuhan Liu, Xun Zhang, Yufei Zhang, Guojun Yin, Fei Jiang, Wei Lin, and Rui Yan. 2025. Beyond static testbeds: An interaction-centric agent simulation platform for dynamic recommender systems. arXiv preprint arXiv:2505.16429. find
  10. Alex Kim and Sangwon Yoon. 2022. Detecting rumor veracity with only textual information by double-channel structure. In Proceedings of the 10th International Workshop on SocialNLP, pages 1–11. NAACL. find
  11. Peter M Krafft, Kate Starbird, and Emma S Spiro. 2019. Keeping rumors in proportion: managing uncertainty in rumor systems. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, pages 1–11. ACM. find
  12. David M. J. Lazer, Matthew A. Baum, Yochai Benkler, Adam J. Berinsky, Kelly M. Greenhill, Filippo Menczer, Miriam J. Metzger, Brendan Nyhan, Gordon Pennycook, David M. Rothschild, Michael Schudson, Steven A. Sloman, Cass Robert Sunstein, Emily A. Thorson, Duncan J. Watts, and Jonathan Zittrain. 2018… find
  13. David MJ Lazer, Matthew A Baum, Yochai Benkler, Adam J Berinsky, Kelly M Greenhill, Filippo Menczer, Miriam J Metzger, Brendan Nyhan, Gordon Pennycook, David Rothschild, et al. 2018b. The science of fake news. Science, 359(6380):1094–1096. find
  14. Quanzhi Li, Xiaomo Liu, Rui Fang, Armineh Nourbakhsh, and Sameena Shah. 2016. User behaviors in newsworthy rumors: A case study of twitter. In Proceedings of the 10th International AAAI Conference on Web and Social Media (ICWSM), volume 10, pages 627–630. AAAI Press. find
  15. Siyu Li, Jin Yang, and Kui Zhao. 2023. Are you in a masquerade? exploring the behavior and impact of large language model driven social bots in online social networks. Preprint, arXiv:2307.10337. — [arXiv:2307.10337](https://arxiv.org/abs/2307.10337) find
  16. Pedro G Lind, Luciano R Da Silva, José S Andrade Jr, and Hans J Herrmann. 2007. Spreading gossip in social networks. Physical Review E—Statistical, Non-linear, and Soft Matter Physics, 76(3):036117. find
  17. Yuhan Liu, Xiuying Chen, Xiaoqing Zhang, Xing Gao, Ji Zhang, and Rui Yan. 2024. From skepticism to acceptance: simulating the attitude dynamics toward fake news. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, pages 7886–7894. find
  18. Yuhan Liu, Yuxuan Liu, Xiaoqing Zhang, Xiuying Chen, and Rui Yan. 2025. The truth becomes clearer through debate! multi-agent systems with large language models unmask fake news. arXiv preprint arXiv:2505.08532. — [arXiv:2505.08532](https://arxiv.org/abs/2505.08532) find
  19. Menglong Lu, Zhen Huang, Binyang Li, Yunxiang Zhao, Zheng Qin, and DongSheng Li. 2022. Sifter: A framework for robust rumor detection. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 30:429–442. find
  20. Jing Ma, Jun Li, Wei Gao, Yang Yang, and Kam-Fai Wong. 2021. Improving rumor detection by promoting information campaigns with transformer-based generative adversarial learning. IEEE Transactions on Knowledge and Data Engineering. find
  21. Charles M Macal and Michael J North. 2005. Tutorial on agent-based modeling and simulation. In Proceedings of the 2005 Winter Simulation Conference, pages 14–25. IEEE. find
  22. Jayawant N Mandrekar. 2011. Measures of interrater agreement. Journal of Thoracic Oncology, 6(1):6–7. find
  23. Mahdieh Mirzabeigi, Mahsa Torabi, and Tahereh Jowkar. 2023. The role of personality traits and the ability to detect fake news in predicting information avoidance during the covid-19 pandemic. Library Hi Tech, 41(2):524–541. find
  24. Yamir Moreno, Maziar Nekovee, and Amalio F Pacheco. 2004. Dynamics of rumor spreading in complex networks. Physical Review E—Statistical, Nonlinear, and Soft Matter Physics, 69(6):066130. find
  25. Yida Mu, Kalina Bontcheva, and Nikolaos Aletras. 2023. It’s about time: Rethinking evaluation on rumor detection benchmarks using chronological splits. In Findings of the Association for Computational Linguistics: EACL 2023, pages 736–743. Association for Computational Linguistics. find
  26. Maziar Nekovee, Yamir Moreno, Ginestra Bianconi, and Matteo Marsili. 2007. Theory of rumour spreading in complex social networks. Physica A: Statistical Mechanics and its Applications, 374(1):457–470. find
  27. Femi Olan, Uchitha Jayawickrama, Emmanuel Ogiem-wonyi Arakpogun, Jana Suklan, and Shaofeng Liu. 2022. Fake news on social media: the impact on society. Information Systems Frontiers, pages 1 – 16. find
  28. Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–22. ACM. find
  29. Joon Sung Park, Lindsay Popowski, Carrie Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2022. Social simulacra: Creating populated prototypes for social computing systems. In Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology, pages 1–18. ACM. find
  30. José Roberto Castilho Piqueira, Mauro Zilbovicius, and Cristiane Mileo Batistela. 2020. Daley–kendal models in fake-news scenario. Physica A: Statistical Mechanics and its Applications, 548:123406. find
  31. Nicolas Pröllochs and Stefan Feuerriegel. 2023. Mechanisms of true and false rumor sharing in social media: collective intelligence or herd behavior? Proceedings of the ACM on Human-Computer Interaction, 7(CSCW2):1–38. find
  32. Wang, Changhao Jiang, Yicheng Zou, Xiangyang Liu, Zhangyue Yin, Shihan Dou, Rongxiang Weng, Wensen Cheng, Qi Zhang, Wenjuan Qin, Yongyan Zheng, Xipeng Qiu, Xuanjing Huang, and Tao Gui. 2023. The rise and potential of large language model based agents: A survey. Preprint, arXiv:2309.07864.
  33. Rui Xia, Kaizhou Xuan, and Jianfei Yu. 2020. A state-independent and time-evolving network for early rumor detection in social media. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 9042–9051. Association for Computational Linguistics. find
  34. Juntian Zhang, Yuhan Liu, Wei Liu, Jian Luan, Rui Yan, et al. 2025. Weaving context across images: Improving vision-language models through focus-centric visual chains. arXiv preprint arXiv:2504.20199. find
  35. Chao Shen, Zhenyu Song, Pengyu He, Limin Liu, and Zhenyu Xiong. 2024. Online rumors during the covid-19 pandemic: co-evolution of themes and emotions. Frontiers in Public Health, 12:1375731. find
  36. Yichao Zhang, Shi Zhou, Zhongzhi Zhang, Jihong Guan, and Shuigeng Zhou. 2013. Rumor evolution in social networks. Physical Review E—Statistical, Nonlinear, and Soft Matter Physics, 87(3):032133. find
  37. Ling Sun, Yuan Rao, Lianwei Wu, Xiangbo Zhang, Yuqian Lan, and Ambreen Nazir. 2023. Fighting false information from propagation process: A survey. ACM Computing Surveys, 55(10):1–38. find
  38. Zheng Zhang, Qi Liu, Zirui Hu, Yi Zhan, Zhenya Huang, Weibo Gao, and Qingyang Mao. 2024. Enhancing fairness in meta-learned user modeling via adaptive sampling. In Proceedings of the ACM Web Conference 2024, pages 3241–3252. find
  39. Petter Törnberg, Diliara Valeeva, Justus Uitermark, and Christopher Bail. 2023. Simulating social media using large language models to evaluate alternative news feed algorithms. Preprint, arXiv:2310.05984. — [arXiv:2310.05984](https://arxiv.org/abs/2310.05984) find
  40. Daniel Trpevski, Wallace KS Tang, and Ljupco Kocarev. 2010. Model for rumor spreading over networks. Physical Review E—Statistical, Nonlinear, and Soft Matter Physics, 81(5):056102. find
  41. Andrea W Wang, Jo-Yu Lan, Chihhao Yu, and Ming-Hung Wang. 2021. The evolution of rumors on a closed platform during covid-19. Preprint, arXiv:2104.13816. — [arXiv:2104.13816](https://arxiv.org/abs/2104.13816) find
  42. Chao Wang, Zong Xuan Tan, Ye Ye, Lu Wang, Kang Hao Cheong, and Neng-gang Xie. 2017. A rumor spreading model based on information entropy. Scientific Reports, 7(1):9615. find
  43. Xinyan Wang, Xiaoming Wang, Fei Hao, Geyong Min, and Liang Wang. 2019. Efficient coupling diffusion of positive and negative information in online social networks. IEEE Transactions on Network and Service Management, 16(3):1226–1239. find
  44. Zheng Zhang, Qi Liu, Hao Jiang, Fei Wang, Yan Zhuang, Le Wu, Weibo Gao, and Enhong Chen. 2023. Fairlisa: fair user modeling with limited sensitive attributes information. In Proceedings of the 37th International Conference on Neural Information Processing Systems, pages 41432–41450. find
  45. Zheng Zhang, Wei Song, Qi Liu, Qingyang Mao, Yiyan Wang, Weibo Gao, Zhenya Huang, Shijin Wang, and Enhong Chen. Towards accurate and fair cognitive diagnosis via monotonic data augmentation. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. find
  46. Shouhao Zhao, Shujuan Ji, Jiandong Lv, and Xianwen Fang. 2024. Propagation tree says: Dynamic evolution characteristics learning approach for rumor detection. International Journal of Machine Learning and Cybernetics, pages 1–17. find
  47. Jiaying Wu, Jiafeng Guo, and Bryan Hooi. 2024. Fake news in sheep’s clothing: Robust fake news detection against llm-empowered style attacks. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 3367–3378. ACM. find
  48. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, Rui Zheng, Xiaoran Fan, Xiao Wang, Limao Xiong, Yuhao Zhou, Weiran find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/liu-2025-stepwise-deception-simulating-evolution-true/