Elamur Research⌕
☰
home / papers / 2026 / Tailoring Rumor Debunking to You: Diversifying Chinese Rumor-Debunking Passages with an LLM-Driven Simulated Feedback-Enhanced Framework

Tailoring Rumor Debunking to You: Diversifying Chinese Rumor-Debunking Passages with an LLM-Driven Simulated Feedback-Enhanced Framework

Paper · 2026 · Xinle Pang, Danding Wang, Qiang Sheng et al.

Summary

Automated fact-checking can explain why a claim is false. Extractive explanations, however, tend to be disjointed, and even fluent LLM-written ones ignore who the reader is. Yet whether a correction works depends on whether its audience accepts it. The authors present MURSE, a framework that generates Chinese rumor-debunking texts tailored to a specific reader type. An LLM first drafts a passage from a rumor and its professional fact-checking evidence, such as that available in CHEF. Three LLM roles then refine it in a loop:

  • a Commenter role-plays a user of a given profile who believes the rumor and posts a comment;
  • an Advisor turns that reaction into revision advice;
  • an Editor rewrites the passage, with access to the rumor and evidence so that facts stay intact.

The loop repeats until checks on sentiment, informativeness and redundancy are satisfied. The full iterative pipeline beats both a generic baseline and a single-revision variant on these measures. In human studies, readers matching the target profile usually chose MURSE texts about two times more often than generic ones. Simulated feedback thus offers an inexpensive route to audience-aware misinformation correction.

Key points

  • MURSE has two components, a Simulated Feedback Module (Commenter + Advisor) and a Passage Refinement Module (Editor). Passages that fail the sentiment, informativeness or redundancy criteria are sent back for another round.
  • User profiles combine gender (2 values), age (4 values) and education (3 values) into 24 profiles, following Nan et al. (2024).
  • Baselines are a "General" passage and a "Single-Round" refinement. The ordering is MURSE > Single-Round > General, and metrics level off from about the 6th iteration.
  • Human evaluation used 20 recruited participants per profile in pairwise comparisons with randomized order. For every profile, user-specific passages won in more than half of the data points, typically 60% or more, while generic passages were rarely favored above 30%.
  • The authors acknowledge two limitations: the three demographic attributes give only shallow user modeling, and LLM-simulated commenters may reflect group stereotypes. The pipeline mixed commercial and open-source LLMs without systematic model selection.

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

🏛️Chinese Academy of SciencesBeijing · China246 works · 24,952 citations🎓University of Chinese Academy of SciencesBeijing · China188 works · 8,744 citations🔬Institute of Computing TechnologyBeijing · China57 works · 3,782 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 worksSocial Sciences · 1,954 worksSociology and Political Science · 626 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,894 works

Cite

Cite as Xinle Pang, Danding Wang, Qiang Sheng, Yifan Sun, Beizhe Hu and Juan Cao. 2026. Tailoring Rumor Debunking to You: Diversifying Chinese Rumor-Debunking Passages with an LLM-Driven Simulated Feedback-Enhanced Framework. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.eacl-industry.45

@inproceedings{pang2026tailoring,
  title = {{Tailoring Rumor Debunking to You: Diversifying Chinese Rumor-Debunking Passages with an LLM-Driven Simulated Feedback-Enhanced Framework}},
  author = {Xinle Pang, Danding Wang, Qiang Sheng, Yifan Sun, Beizhe Hu and Juan Cao},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-industry.45},
  url = {https://doi.org/10.18653/v1/2026.eacl-industry.45}
}

References

43 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma, and Isabelle Augenstein. 2020. Generating fact checking explanations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7352–7364, Online. Association for Computational Linguistics.
  2. Melisa Basol, Jon Roozenbeek, and Sander van der Linden. 2020. Good news about bad news: Gamified inoculation boosts confidence and cognitive immunity against fake news. Journal of Cognition. find
  3. Man-pui Sally Chan, Christopher R Jones, Kathleen Hall Jamieson, and Dolores Albarracín. 2017. Debunking: A meta-analysis of the psychological efficacy of messages countering misinformation. Psychological science, 28(11):1531–1546. find
  4. Jonas De keersmaecker and Arne Roets. 2017. ‘fake news’: Incorrect, but hard to correct. the role of cognitive ability on the impact of false information on social impressions. Intelligence, 65:107–110. find
  5. Islam Eldifrawi, Shengrui Wang, and Amine Trabelsi. 2024. Automated justification production for claim veracity in fact checking: A survey on architectures and approaches. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6679–6… find
  6. Joseph Gatto, Omar Sharif, and Sarah Preum. 2023. Chain-of-thought embeddings for stance detection on social media. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4154– 4161, Singapore. Association for Computational Linguistics. ings of the ACM on Human-Computer Inte…
  7. Kyungha Kim, Sangyun Lee, Kung-Hsiang Huang, Hou Pong Chan, Manling Li, and Heng Ji. 2024. Can llms produce faithful explanations for fact-checking? towards faithful explainable fact-checking via multi-agent debate. Preprint, arXiv:2402.07401. — [arXiv:2402.07401](https://arxiv.org/abs/2402.07401) find
  8. Emily Vraga Kjerstin Thorson and Brian Ekdale. 2010. Credibility in context: How uncivil online commentary affects news credibility. Mass Communication and Society, 13(3):289–313. find
  9. Bin Guo, Yasan Ding, Lina Yao, Yunji Liang, and Zhiwen Yu. 2020. The future of false information detection on social media: New perspectives and trends. ACM Computing Surveys, 53(4). find
  10. Neema Kotonya and Francesca Toni. 2020a. Explainable automated fact-checking: A survey. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5430–5443. International Committee on Computational Linguistics. find
  11. Bing He, Mustaque Ahamad, and Srijan Kumar. 2023. Reinforcement learning-based counter-misinformation response generation: A case study of covid-19 vaccine misinformation. In Proceedings of the ACM Web Conference 2023, pages 2698–2709. Association for Computing Machinery. find
  12. Neema Kotonya and Francesca Toni. 2020b. Explainable automated fact-checking for public health claims. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7740–7754, Online. Association for Computational Linguistics.
  13. Han He and Jinho D. Choi. 2021. The stem cell hypothesis: Dilemma behind multi-task learning with transformer encoders. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5555–5577. Association for Computational Linguistics. find
  14. 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 Rothschild, Michael Schudson, Steven A. Sloman, Cass R. Sunstein, Emily A. Thorson, Duncan J. Watts, and Jonathan L. Zittrain. 2018. Th… find
  15. Beizhe Hu, Qiang Sheng, Juan Cao, Yang Li, and Danding Wang. 2025. Llm-generated fake news induces truth decay in news ecosystem: A case study on neural news recommendation. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 435–… find
  16. Shengding Hu, Yuge Tu, Xu Han, Chaoqun He, Ganqu Cui, Xiang Long, Zhi Zheng, Yewei Fang, Yuxiang Huang, Weilin Zhao, Xinrong Zhang, Zheng Leng Thai, Kaihuo Zhang, Chongyi Wang, Yuan Yao, Chenyang Zhao, Jie Zhou, Jie Cai, Zhongwu Zhai, Ning Ding, Chao Jia, Guoyang Zeng, Dahai Li, Zhiyuan Liu, and Mao… — MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
  17. Xuming Hu, Zhijiang Guo, GuanYu Wu, Aiwei Liu, Lijie Wen, and Philip Yu. 2022. CHEF: A pilot Chinese dataset for evidence-based fact-checking. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3362… find
  18. Shan Jiang and Christo Wilson. 2018. Linguistic signals under misinformation and fact-checking: Evidence from user comments on social media. find
  19. Proceed-Stephan Lewandowsky, Ullrich K. H. Ecker, Colleen M. Seifert, Norbert Schwarz, and John Cook. 2012. Misinformation and its correction: Continued influence and successful debiasing. Psychological Science in the Public Interest, 13(3):106–131. find
  20. Aiwei Liu, Qiang Sheng, and Xuming Hu. 2024. Preventing and detecting misinformation generated by large language models. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 3001–3004. Association for Computing Machinery. find
  21. Jing Ma, Wei Gao, and Kam Fai Wong. 2018. Detect rumor and stance jointly by neural multi-task learning. In Companion Proceedings of the Web Conference 2018, pages 585–593. Association for Computing Machinery. find
  22. Yingchen Ma, Bing He, Nathan Subrahmanian, and Srijan Kumar. 2023. Characterizing and predicting social correction on twitter. In Proceedings of the 15th ACM Web Science Conference 2023, pages 86– 95. Association for Computing Machinery. find
  23. Diana Micevičienė, Kara Lina Guokė, Jan Rajchel, et al. 2024. Fake news in the socio-economic environment in the context of the war in ukraine. Central European Journal of Security Studies, 2(1):97–104. find
  24. Qiong Nan, Qiang Sheng, Juan Cao, Beizhe Hu, Danding Wang, and Jintao Li. 2024. Let silence speak: Enhancing fake news detection with generated comments from large language models. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, page 1732–1742. Associ… find
  25. Qiong Nan, Qiang Sheng, Juan Cao, Yongchun Zhu, Danding Wang, Guang Yang, and Jintao Li. 2025. Exploiting user comments for early detection of fake news prior to users’ commenting. Frontiers of Computer Science, 19(10):1910354. find
  26. OpenAI. 2024. Gpt-4o system card. arXiv:2410.21276.
  27. Preprint, Maryke S Steffens, Adam G Dunn, Kerrie E Wiley, and Julie Leask. 2019. How organisations promoting vaccination respond to misinformation on social media: a qualitative investigation. BMC public health, 19:1–12. find
  28. Yifan Sun, Danding Wang, Qiang Sheng, Juan Cao, and Jintao Li. 2025. Enhancing the comprehensibility of text explanations via unsupervised concept discovery. In Findings of the Association for Computational Linguistics: ACL 2025, pages 14695–14713, Vienna, Austria. Association for Computational Ling… find
  29. Team GLM. 2024. Chatglm: A family of large language models from glm-130b to glm-4 all tools. Preprint, arXiv:2406.12793.
  30. Gordon Pennycook and David G. Rand. 2019. Lazy, not biased: Susceptibility to partisan fake news is better explained by lack of reasoning than by motivated reasoning. Cognition, 188:39–50. The Cognitive Science of Political Thought. find
  31. Francesco Pierri, Brea L Perry, Matthew R DeVerna, Kai-Cheng Yang, Alessandro Flammini, Filippo Menczer, and John Bryden. 2022. Online misinformation is linked to early covid-19 vaccination hesitancy and refusal. Scientific reports, 12(1):5966. find
  32. Zhongyi Qiu, Hanjia Lyu, Wei Xiong, and Jiebo Luo. 2025. Can llms simulate social media engagement? a study on action-guided response generation. Preprint, arXiv:2502.12073. — [arXiv:2502.12073](https://arxiv.org/abs/2502.12073) find
  33. Daniel Russo, Shane Kaszefski-Yaschuk, Jacopo Staiano, and Marco Guerini. 2023a. Countering misinformation via emotional response generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11476– 11492. Association for Computational Linguistics. find
  34. Daniel Russo, Stefano Menini, Jacopo Staiano, and Marco Guerini. 2025. Face the facts! evaluating RAG-based pipelines for professional fact-checking. In Proceedings of the 18th International Natural Language Generation Conference, pages 846–865, Hanoi, Vietnam. Association for Computational Linguist… find
  35. Daniel Russo, Serra Sinem Tekiroğlu, and Marco Guerini. 2023b. Benchmarking the generation of fact checking explanations. Transactions of the Association for Computational Linguistics, 11:1250–1264. find
  36. Devendra Sachan, Mike Lewis, Mandar Joshi, Armen Aghajanyan, Wen-tau Yih, Joelle Pineau, and Luke Zettlemoyer. 2022. Improving passage retrieval with zero-shot question generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3781–3797, Abu Dhabi,…
  37. Kai Shu, Suhang Wang, and Huan Liu. 2019. Beyond news contents: The role of social context for fake news detection. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pages 312–320. find
  38. Herun Wan, Shangbin Feng, Zhaoxuan Tan, Heng Wang, Yulia Tsvetkov, and Minnan Luo. 2024. DELL: Generating reactions and explanations for LLM-based misinformation detection. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2637–2667. Association for Computational Linguist… find
  39. Zhengjia Wang, Qiang Sheng, Danding Wang, Beizhe Hu, and Juan Cao. 2025a. Bridging thoughts and words: Graph-based intent-semantic joint learning for fake news detection. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management, pages 3250–3260. Association for… find
  40. Zhengjia Wang, Danding Wang, Qiang Sheng, Juan Cao, Siyuan Ma, and Haonan Cheng. 2025b. Exploring news intent and its application: A theory-driven approach. Information Processing & Management, 62(6):104229. find
  41. 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. International Commi… find
  42. Zhenrui Yue, Huimin Zeng, Yimeng Lu, Lanyu Shang, Yang Zhang, and Dong Wang. 2024. Evidence-driven retrieval augmented response generation for online misinformation. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language T… find
  43. Xueyao Zhang, Juan Cao, Xirong Li, Qiang Sheng, Lei Zhong, and Kai Shu. 2021. Mining dual emotion for fake news detection. In Proceedings of the Web Conference 2021, pages 3465–3476. Association for Computing Machinery. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/pang-2026-tailoring-rumor-debunking-you-diversifying/