Elamur Research⌕
☰
home / papers / 2026 / Beyond Static Artifacts: An Evolutionary Framework for Synthetic Claim Generation

Beyond Static Artifacts: An Evolutionary Framework for Synthetic Claim Generation

Paper · 2026 · Yeqing Teng, Jiasheng Si, Shuxia Lin et al.

Summary

Most claim detection benchmarks treat claims as fixed sentences, either mined from sources such as political debates or filled into LLM templates. They ignore how claims actually change as they spread through social networks. The authors instead simulate claim evolution with multiple agents, based on the Open Claims Model, which splits a claim into Context, Utterance and Proposition.

Generation starts from news-based seed contexts, which yield seed-claims and non-claims. Seeds then pass along chains of simulated users in two modes:

  • Unmitigated propagation: free rewriting lets veracity drift appear on its own.
  • Intervened propagation: auditor agents steer each claim toward a chosen target value on a given dimension.

Check-worthiness is recast through the BUP (background-user-perspective) framework as a probability that depends on social conditions, not a fixed label. The outputs are Seed, Middle and Evolved datasets. Evolved claims proved harder to detect than seeds, and the simulation reproduced "truth decay." This makes the resource useful for stress-testing fact-checking pipelines under realistic propagation noise.

Key points

  • Intervened propagation offers control over five dimensions: Stance Polarity, Causal Structure, Expression Type, Message Granularity and Linguistic Style. Verdict Level is also studied as an evolution target.
  • With multi-auditor review, target values were reached in over 85% of cases on every controlled dimension, and above 90% on several. This beat both one-shot generation and a single-auditor setup.
  • LLM annotation was checked with Cohen's κ (substantial agreement) and manual sampling audits. After closed-loop filtering, all three data types kept more than 95% of items.
  • Topics include COVID-19, Russia-Ukraine, Health, US-Elections and Regional news. Check-worthiness scores shift with user education level and with the value perspectives used for evaluation.
  • Code and data: github.com/yeqingteng/Beyond-Static-Artifacts. Stated limitations are heavy reliance on LLMs, with limited human validation, and static user attributes without memory or belief updating.

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

🎓King's College LondonLondon · United Kingdom42 works · 1,617 citations🎓Southeast UniversityNanjing · China28 works · 354 citations

 Fields, topics and concepts

📚 Shelves 5The 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 works

Cite

Cite as Yeqing Teng, Jiasheng Si, Shuxia Lin, Linhai Zhang, Weiyu Zhang, Wenpeng Lu, Deyu Zhou and Xiaoming Wu. 2026. Beyond Static Artifacts: An Evolutionary Framework for Synthetic Claim Generation. 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.1548

@inproceedings{teng2026beyond,
  title = {{Beyond Static Artifacts: An Evolutionary Framework for Synthetic Claim Generation}},
  author = {Yeqing Teng, Jiasheng Si, Shuxia Lin, Linhai Zhang, Weiyu Zhang, Wenpeng Lu, Deyu Zhou and Xiaoming Wu},
  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.1548},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1548}
}

References

56 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Noushin Salek Faramarzi, Fateme Hashemi Chaleshtori, Hossein Shirazi, Indrakshi Ray, and Ritwik Banerjee. 2023. Claim extraction and dynamic stance detection in COVID-19 tweets. In Companion Proceedings of the ACM Web Conference 2023, pages 1059–1068. find
  2. Lada A. Adamic, Thomas M. Lento, Eytan Adar, and Pauline C. Ng. 2016. Information evolution in social networks. In Proceedings of the ninth ACM international conference on web search and data mining, pages 473–482. find
  3. Martin Arjovsky, Soumith Chintala, and Léon Bottou. 2017. Wasserstein generative adversarial networks. In Proceedings of the 34th International Conference on Machine Learning, pages 214–223. find
  4. Furkan Arslan, Naeemul Hassan, Chengkai Li, Mark Tremayne, Bill Adair, and Di Xin. 2020. A benchmark dataset of check-worthy factual claims. In Proceedings of the International AAAI Conference on Web and Social Media, pages 821–829. find
  5. Eytan Bakshy, Seth Messing, and Lada A. Adamic. 2015. Exposure to ideologically diverse news and opinion on facebook. Science, 348(6239):1130– 1132. find
  6. K. Boland, P. Fafalios, A. Tchechmedjiev, and et al. 2022. Beyond facts: A survey and conceptualisation of claims in online discourse analysis. Semantic Web, 13(5):793–827. find
  7. Samantha Bradshaw and Philip N. Howard. 2018. The global organization of social media disinformation campaigns. Journal of International Affairs, 71(1.5):23–32. find
  8. Jean-Flavien Bussotti, Luca Ragazzi, Giacomo Frisoni, Gianluca Moro, and Paolo Papotti. 2024. Unknown Claims: Generation of fact-checking training examples from unstructured and structured data. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 12105– 1… find
  9. Elizabeth Clark, Tal August, Sofia Serrano, Niket Tandon, Suchin Gururangan, and Noah A. Smith. 2021. All that’s “human” is not gold: Evaluating human evaluation of generated text. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International J… find
  10. Robin I. M. Dunbar. 1992. Neocortex size as a constraint on group size in primates. Journal of Human Evolution, 22(6):469–493. find
  11. Subhabrata Dutta, Rudra Dhar, Prantik Guha, Arpan Murmu, and Dipankar Das. 2022. A multilingual dataset for identification of factual claims in indian twitter. In Proceedings of the 14th Annual Meeting of the Forum for Information Retrieval Evaluation, pages 88–92. find
  12. Akash Ghosh, Aparna Garimella, Pritika Ramu, Sambaran Bandyopadhyay, and Sriparna Saha. 2025. In-foGen: Generating complex statistical infographics from documents. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, pages 20552–20570. find
  13. Nir Grinberg, Kenneth Joseph, Lisa Friedland, Briony Swire-Thompson, and David Lazer. 2019. Fake news on twitter during the 2016 u.s. presidential election. Science, 363(6425):374–378. find
  14. Andrew Guess, Jonathan Nagler, and Joshua Tucker. 2019. Less than you think: Prevalence and predictors of fake news dissemination on facebook. Science Advances, 5(1):1–8. find
  15. Zhiji Guo, Michael Schlichtkrull, and Andreas Vlachos. 2022. A survey on automated fact-checking. Transactions of the Association for Computational Linguistics, 10:178–206.
  16. Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2023. DeBERTaV3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. In Proceedings of the Eleventh International Conference on Learning Representations, pages 1– 16.
  17. Ronald F. Inglehart and Christian Welzel. 2005. Modernization, Cultural Change and Democracy: The Human Development Sequence. Cambridge University Press, Cambridge, UK. find
  18. Fang Jin, Edward Dougherty, Parang Saraf, Yang Cao, and Naren Ramakrishnan. 2013. Epidemiological modeling of news and rumors on twitter. In Proceedings of the 7th Workshop on Social Network Mining and Analysis, pages 1–9. find
  19. Roger E. Kasperson, Ortwin Renn, Paul Slovic, Halina S. Brown, Jacque Emel, Robert Goble, Jeanne Kasperson, and Samuel Ratick. 1988. The social amplification of risk: A conceptual framework. Risk Analysis, 8(2):177–187. find
  20. Jan-Christoph Klie, Richard Eckart de Castilho, and Iryna Gurevych. 2024. Analyzing dataset annotation quality management in the wild. Computational Linguistics, 50(3):817–896.
  21. Lev Konstantinovskiy, Oliver Price, Will Babakar, and Arkaitz Zubiaga. 2021. Toward automated factchecking: Developing an annotation schema and benchmark for consistent automated claim detection. Digital Threats: Research and Practice, 2(2):1–16. find
  22. Matthew A. Lawson and Hemant K. Kakkar. 2022. Of pandemics, politics, and personality: The role of conscientiousness and political ideology in the sharing of fake news. Journal of Experimental Psychology: General, 151(5):1–24. find
  23. 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
  24. Chance Jiajie Li, Jiayi Wu, Zhenze Mo, Ao Qu, Yuhan Tang, Kaiya Ivy Zhao, Yulu Gan, Jie Fan, Jiangbo Yu, Jinhua Zhao, Paul Pu Liang, Luis Alonso, and Kent Larson. 2025a. Simulating society requires simulating thought. In Proceedings of the Thirty-Ninth Annual Conference on Neural Information Process… find
  25. Y. Li, Q. Zhang, W. Lu, and et al. 2025b. Time-aware medication recommendation via intervention of dynamic treatment regimes. In Proceedings of the ACM Web Conference 2025, pages 5161–5172. find
  26. 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
  27. 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.
  28. Jason Lucas, Adaku Uchendu, Michiharu Yamashita, Jooyoung Lee, Shaurya Rohatgi, and Dongwon Lee. 2023. Fighting fire with fire: The dual role of LLMs in crafting and detecting elusive disinformation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 142… find
  29. Rui Ma, Xue Wang, and Guang R. Yang. 2025. Fighting fake news in the age of generative ai: Strategic insights from multi-stakeholder interactions. Technological Forecasting and Social Change, 216:1–22. find
  30. Raj Gaurav Maurya, Vaibhav Shukla, Raj Abhijit Dandekar, Rajat Dandekar, and Sreedath Panat. 2025. Simulating misinformation propagation in social networks using large language models. arXiv preprint arXiv:2511.10384. — [arXiv:2511.10384](https://arxiv.org/abs/2511.10384) find
  31. Dasha Metropolitansky and Jonathan Larson. 2025. Towards effective extraction and evaluation of factual claims. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, pages 6996–7045.
  32. Preslav Nakov, Alberto Barrón-Cedeño, Giovanni Da San Martino, Firoj Alam, Rubén Míguez, Tommaso Caselli, Mucahid Kutlu, Wajdi Zaghouani, Chengkai Li, Shaden Shaar, Hamdy Mubarak, Alex Nikolov, and Yavuz Selim Kartal. 2022. Overview of the CLEF-2022 CheckThat! lab task 1 on identifying relevant clai… find
  33. Jingwei Ni, Mingyang Shi, Dominik Stammbach, Nathanael Schärli, Adina Williams, and Robert West. 2024. AFaCTA: Assisting the annotation of factual claim detection with reliable LLM annotators. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, pages 1890– 191… find
  34. Raúl Ortega and Jose Manuel Gomez-Perez. 2025. Sciclaims: An end-to-end generative system for biomedical claim analysis. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 141–154.
  35. Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, and William Yang Wang. 2021. Zero-shot fact verification by claim generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (V… find
  36. Rajalakshmi Panchendrarajan and Arkaitz Zubiaga. 2024. Claim detection for automated fact-checking: A survey on monolingual, multilingual and cross-lingual research. Natural Language Processing Journal, 7:1–15. find
  37. Gordon Pennycook and David G. Rand. 2021. The psychology of fake news. Trends in Cognitive Sciences, 25(5):388–402. find
  38. Jinghua Piao, Yuwei Yan, Nian Li, Jun Zhang, and Yong Li. 2024. Exploring large language model agents for piloting social experiments. In Proceedings of the Second Conference on Language Modeling, pages 1–25. find
  39. Jinghua Piao, Yuwei Yan, Jun Zhang, Nian Li, Junbo Yan, Xiaochong Lan, Zhihong Lu, Zhiheng Zheng, Jing Yi Wang, Di Zhou, Chen Gao, Fengli Xu, Fang Zhang, Ke Rong, Jun Su, and Yong Li. 2025. Agentsociety: Large-scale simulation of LLM-driven generative agents advances understanding of human behaviors… — [arXiv:2502.08691](https://arxiv.org/abs/2502.08691) find
  40. Cristina M. Pulido, Beatriz Villarejo-Carballido, Gisela Redondo-Sama, and Aitor Gómez. 2020. Covid-19 infodemic: More retweets for science-based information on coronavirus than for false information. International Sociology, 35(4):377–392. find
  41. Brennen J. S., Simon F. M., Howard P. N., and Nielsen R. K. 2020. Types, sources, and claims of covid-19 misinformation. Reuters Institute for the Study of Journalism, pages 1–13. find
  42. Shaden Shaar, Firoj Alam, Giovanni Da San Martino, Alex Nikolov, Wajdi Zaghouani, Preslav Nakov, and Anna Feldman. 2021. Findings of the NLP4IF-2021 shared tasks on fighting the COVID-19 infodemic and censorship detection. In Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship… find
  43. Jiasheng Si, Yao Zhu, Wenpeng Lu, and 1 others. 2024. Denoising rationalization for multi-hop fact verification via multi-granular explainer. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 12593–12608. find
  44. Nicholas Sukiennik, Yichuan Xu, Yuqing Kan, Jinghua Piao, Yuwei Yan, Chen Gao, and Yong Li. 2025. The roots of international perceptions: Simulating US attitude changes towards china with LLM agents. arXiv preprint arXiv:2508.08837. — [arXiv:2508.08837](https://arxiv.org/abs/2508.08837) find
  45. Soroush Vosoughi, Deb Roy, and Sinan Aral. 2018. The spread of true and false news online. Science, 359(6380):1146–1151. find
  46. Ivan Vykopal, Matúš Pikuliak, Ivan Srba, Robert Moro, Dominik Macko, and Maria Bielikova. 2024. Disinformation capabilities of large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, pages 14830– 14847. find
  47. Lionel Z. Wang, Yiming Ma, Renfei Gao, Beichen Guo, Han Zhu, Wenqi Fan, Zexin Lu, and Ka Chung Ng. 2024. Megafake: A theory-driven dataset of fake news generated by large language models. arXiv preprint arXiv:2408.11871. — [arXiv:2408.11871](https://arxiv.org/abs/2408.11871) find
  48. J. Wu, J. Guo, and B. 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. find
  49. Guiqiong Xu, Meng Qian, and Lei Meng. 2025. Misinformation dissemination on social media: key research themes and evolutionary paths between 2013 and 2023. Humanities and Social Sciences Communications, 12(1):1–15. find
  50. Yuwei Yan, Jinghua Piao, Xiaochong Lan, Chenyang Shao, Pan Hui, and Yong Li. 2025. Simulating generative social agents via theory-informed workflow design. arXiv preprint arXiv:2508.08726. — [arXiv:2508.08726](https://arxiv.org/abs/2508.08726) find
  51. Yuzhe Yang, Yifei Zhang, Minghao Wu, Kaidi Zhang, Yunmiao Zhang, Honghai Yu, Yan Hu, and Benyou Wang. 2025. Twinmarket: A scalable behavioral and social simulation for financial markets. In ICLR 2025 Workshop on World Models: Understanding, Modelling and Scaling, pages 1–34. find
  52. Xinnong Zhang, Jiayu Lin, Xinyi Mou, Shiyue Yang, Xiawei Liu, Libo Sun, Hanjia Lyu, Yihang Yang, Weihong Qi, Yue Chen, Guanying Li, Ling Yan, Yao Hu, Siming Chen, Yu Wang, Xuanjing Huang, Jiebo Luo, Shiping Tang, Libo Wu, and 2 others. 2025a. Socioverse: A world model for social simulation powered b… — [arXiv:2504.10157](https://arxiv.org/abs/2504.10157) find
  53. Yunyao Zhang, Zikai Song, Hang Zhou, Wenfeng Ren, Yi-Ping Phoebe Chen, Junqing Yu, and Wei Yang. 2025b. GA-S 3 : Comprehensive social network simulation with group agents. In Findings of the Association for Computational Linguistics: ACL 2025, pages 8950–8970. find
  54. X. Zhao, W. Lu, C. Zheng, and et al. 2025. Plan dynamically, express rhetorically: A debate-driven rhetorical framework for argumentative writing. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 9562–9584. find
  55. Siying Zhou, Yiquan Wu, Hui Chen, Xueyu Hu, Kun Kuang, Adam Jatowt, Chunyan Zheng, and Fei Wu. 2025. ClaimGen-CN: A large-scale chinese dataset for legal claim generation. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 12296–12323. find
  56. Arkaitz Zubiaga, Maria Liakata, Rob Procter, Geraldine Wong Sak Hoi, and Peter Tolmie. 2016. Analysing how people orient to and spread rumours in social media by looking at conversational threads. PloS One, 11(3):1–29. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/teng-2026-beyond-static-artifacts-evolutionary-framework/