Elamur Research⌕
☰
home / papers / 2026 / ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction

ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction

Paper · 2026 · Lvhua Wu, Xuefeng Jiang, Sheng Sun et al.

Summary

ZoFia targets zero-shot fake news detection, where LLMs struggle for two reasons. Their knowledge cutoff leads to hallucinated facts about recent events. A single model also tends to commit to a verdict early and then justify it, so it handles content analysis and fact checking poorly at the same time.

The framework has two stages. In the first, a BERT-NER model proposes candidate entities. These are ranked with a new Hierarchical Salience score, which combines entity–context and context–document SBERT similarities. A Salience-Calibrated MMR (SC-MMR) step then picks a compact keyword set, which forms a conjunctive query for Wikipedia and Open Web retrieval. In the second stage, several LLM agents work in parallel: a linguistic analyst, a domain expert, and a claim extractor/verifier. Opposing debaters then argue "real" and "fake," and a judge issues the verdict.

On two public datasets, ZoFia beats zero-shot baselines and most few-shot methods. This matters because it shows that separating reasoning from evidence checking makes training-free detection more reliable and explainable.

Key points

  • Agent roles are Linguist, Expert, Claim Extractor/Verifier, Debater-R, Debater-F and Judge, tested with backbones including Qwen3-32B and DeepSeek-v3. Code is released at github.com/SakiRinn/ZoFia.
  • On GossipCop with Qwen3-32B, ZoFia reaches 69.71 accuracy and 59.07 F1. Without retrieval, these fall to 62.65 and 50.85.
  • Swapping the entity extraction for TF-IDF, PromptNER or LLM-only NER lowers F1 by 5.69, 3.94 and 6.33 points. Sentence-level queries (Sentence Salience, Core Claim) or OR-based matching lower it by 12.92, 10.26 and 6.81 points.
  • Performance holds steady up to about 6 keywords and drops sharply beyond that. This motivated an annealed SC-MMR weight with α = 0.3 and β = 2.5.
  • Under output-token limits, CoT and FactAgent level off around 600 tokens. ZoFia needs at least 400 tokens and keeps improving up to 1200.

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 · China194 works · 23,906 citations🎓University of Chinese Academy of SciencesBeijing · China147 works · 8,480 citations🔬Institute of Computing TechnologyBeijing · China51 works · 3,411 citations

 Fields, topics and concepts

📚 Shelves 7The 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 worksSocial Sciences · 1,772 worksInformation Systems · 1,437 worksSociology and Political Science · 577 works

🧭 Topics 1Research subjects and languages the work is about.Information retrieval & search · 473 works

Cite

Cite as Lvhua Wu, Xuefeng Jiang, Sheng Sun, Yan Lei, Tian Wen, Yuwei Wang and Min Liu. 2026. ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction. 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.1083

@inproceedings{wu2026zofia,
  title = {{ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction}},
  author = {Lvhua Wu, Xuefeng Jiang, Sheng Sun, Yan Lei, Tian Wen, Yuwei Wang and Min Liu},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1083},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1083}
}

References

55 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Dhananjay Ashok and Zachary C Lipton. 2023. Promptner: Prompting for named entity recognition. arXiv preprint arXiv:2305.15444.
  2. Vian Bakir and Andrew McStay. 2018. Fake news and the economy of emotions: Problems, causes, solutions. Digital journalism, 6(2):154–175. find
  3. Benjamin Bullough, Harrison Lundberg, Chen Hu, and Weihang Xiao. 2024. Predicting entity salience in extremely short documents. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 50–64. find
  4. Jaime Carbonell and Jade Goldstein. 1998. The use of mmr, diversity-based reranking for reordering documents and producing summaries. In Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval, pages 335–336. find
  5. Claudio Carpineto and Giovanni Romano. 2012. A survey of automatic query expansion in information retrieval. Acm Computing Surveys (CSUR), 44(1):1– 50. find
  6. Chi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu, Wei Xue, Shanghang Zhang, Jie Fu, and Zhiyuan Liu. 2023. Chateval: Towards better llm-based evaluators through multi-agent debate. arXiv preprint arXiv:2308.07201.
  7. Canyu Chen and Kai Shu. 2023. Can llm-generated misinformation be detected? arXiv preprint arXiv:2309.13788. find
  8. Jeffrey Cheng, Marc Marone, Orion Weller, Dawn Lawrie, Daniel Khashabi, and Benjamin Van Durme. 2024. Dated data: Tracing knowledge cutoffs in large language models. arXiv preprint arXiv:2403.12958. find
  9. Weiqi Hu, Ye Wang, Yan Jia, Qing Liao, and Bin Zhou. 2024c. A multi-modal prompt learning framework for early detection of fake news. In Proceedings of the International AAAI Conference on Web and Social Media, volume 18, pages 651–662. find
  10. DeepSeekAI. 2024. Deepseekv3 technical report. Preprint, arXiv:2412.19437. find
  11. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of hallucination in natural language generation. ACM computing surveys, 55(12):1–38.
  12. Chunyuan Deng, Yilun Zhao, Xiangru Tang, Mark Gerstein, and Arman Cohan. 2023. Investigating data contamination in modern benchmarks for large language models. arXiv preprint arXiv:2311.09783.
  13. Jesse Dunietz and Dan Gillick. 2014. A new entity salience task with millions of training examples. In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers, pages 205–209.
  14. Jessica Maria Echterhoff, Yao Liu, Abeer Alessa, Julian McAuley, and Zexue He. 2024. Cognitive bias in decision-making with llms. In Findings of the association for computational linguistics: EMNLP 2024, pages 12640–12653. find
  15. Marc Fisher, John Woodrow Cox, and Peter Hermann. 2016. Pizzagate: From rumor, to hashtag, to gunfire in dc. Washington Post, 6:8410–8415. find
  16. In Gim, Guojun Chen, Seung-seob Lee, Nikhil Sarda, Anurag Khandelwal, and Lin Zhong. 2024. Prompt cache: Modular attention reuse for low-latency inference. Proceedings of Machine Learning and Systems, 6:325–338. find
  17. Hao Guo, Zihan Ma, Zhi Zeng, Minnan Luo, Weixin Zeng, Jiuyang Tang, and Xiang Zhao. 2025. Each fake news is fake in its own way: An attribution multi-granularity benchmark for multimodal fake news detection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 228–236. find
  18. Feng Hou, Ruili Wang, Jun He, and Yi Zhou. 2021. Improving entity linking through semantic reinforced entity embeddings. arXiv preprint arXiv:2106.08495. find
  19. Nathaniel Hoy and Theodora Koulouri. 2022. Exploring the generalisability of fake news detection models. In 2022 IEEE International Conference on Big Data (Big Data), pages 5731–5740. IEEE. find
  20. Beizhe Hu, Qiang Sheng, Juan Cao, Yuhui Shi, Yang Li, Danding Wang, and Peng Qi. 2024a. Bad actor, good advisor: Exploring the role of large language models in fake news detection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 22105–22113. find
  21. Beizhe Hu, Qiang Sheng, Juan Cao, Yuhui Shi, Yang Li, Danding Wang, and Peng Qi. 2024b. Bad actor, good advisor: Exploring the role of large language models in fake news detection. In Proceedings of the AAAI conference on artificial intelligence, volume 38, pages 22105–22113. find
  22. Gongyao Jiang, Shuang Liu, Yu Zhao, Yueheng Sun, and Meishan Zhang. 2022. Fake news detection via knowledgeable prompt learning. Information Processing & Management, 59(5):103029. find
  23. Xuefeng Jiang, Lvhua Wu, Sheng Sun, Jia Li, Jingjing Xue, Yuwei Wang, Tingting Wu, and Min Liu. 2024. Investigating large language models for code vulnerability detection: An experimental study. arXiv preprint arXiv:2412.18260. — [arXiv:2412.18260](https://arxiv.org/abs/2412.18260) find
  24. Weiqiang Jin, Yang Gao, Tao Tao, Xiujun Wang, Ningwei Wang, Baohai Wu, and Biao Zhao. 2025. Veracity-oriented context-aware large language modelsbased prompting optimization for fake news detection. International Journal of Intelligent Systems, 2025(1):5920142. find
  25. Yiqiao Jin, Minje Choi, Gaurav Verma, Jindong Wang, and Srijan Kumar. 2024. Mm-soc: Benchmarking multimodal large language models in social media platforms. arXiv preprint arXiv:2402.14154. find
  26. Rohit Kumar Kaliyar, Anurag Goswami, and Pratik Narang. 2021. Fakebert: Fake news detection in social media with a bert-based deep learning approach. Multimedia tools and applications, 80(8):11765– 11788. find
  27. Soveatin Kuntur, Anna WrĂłblewska, Marcin Paprzycki, and Maria Ganzha. 2024. Fake news detection: It’s all in the data! arXiv preprint arXiv:2407.02122. — [arXiv:2407.02122](https://arxiv.org/abs/2407.02122) find
  28. Xiaochong Lan, Chen Gao, Depeng Jin, and Yong Li. 2024. Stance detection with collaborative role-infused llm-based agents. In Proceedings of the international AAAI conference on web and social media, volume 18, pages 891–903. find
  29. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, and 1 others. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems, 33:9459–…
  30. Jia Li, Lijie Hu, Zhixian He, Jingfeng Zhang, Tianhang Zheng, and Di Wang. 2024a. Text guided image editing with automatic concept locating and forgetting. arXiv preprint arXiv:2405.19708. — [arXiv:2405.19708](https://arxiv.org/abs/2405.19708) find
  31. Jia Li, Lijie Hu, Jingfeng Zhang, Tianhang Zheng, Hua Zhang, and Di Wang. 2025. Fair text-to-image diffusion via fair mapping. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 26256–26264. find
  32. Xinyi Li, Yongfeng Zhang, and Edward C Malthouse. 2024b. Large language model agent for fake news detection. arXiv preprint arXiv:2405.01593. — [arXiv:2405.01593](https://arxiv.org/abs/2405.01593) find
  33. Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Shuming Shi, and Zhaopeng Tu. 2023. Encouraging divergent thinking in large language models through multi-agent debate. arXiv preprint arXiv:2305.19118.
  34. Ye Liu, Jiajun Zhu, Kai Zhang, Haoyu Tang, Yanghai Zhang, Xukai Liu, Qi Liu, and Enhong Chen. 2024. Detect, investigate, judge and determine: A novel llm-based framework for few-shot fake news detection. arXiv preprint arXiv:2407.08952. — [arXiv:2407.08952](https://arxiv.org/abs/2407.08952) find
  35. 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. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages… find
  36. Federico Monti, Fabrizio Frasca, Davide Eynard, Damon Mannion, and Michael M Bronstein. 2019. Fake news detection on social media using geometric deep learning. arXiv preprint arXiv:1902.06673. — [arXiv:1902.06673](https://arxiv.org/abs/1902.06673) find
  37. Qiong Nan, Juan Cao, Yongchun Zhu, Yanyan Wang, and Jintao Li. 2021. Mdfend: Multi-domain fake news detection. In Proceedings of the 30th ACM international conference on information & knowledge management, pages 3343–3347. find
  38. 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, pages 1732– 1742. find
  39. Bo Ni, Zhichun Guo, Jianing Li, and Meng Jiang. 2020. Improving generalizability of fake news detection methods using propensity score matching. arXiv preprint arXiv:2002.00838. — [arXiv:2002.00838](https://arxiv.org/abs/2002.00838) find
  40. Cheng Niu, Yang Guan, Yuanhao Wu, Juno Zhu, Juntong Song, Randy Zhong, Kaihua Zhu, Siliang Xu, Shizhe Diao, and Tong Zhang. 2024. Veract scan: Retrieval-augmented fake news detection with justifiable reasoning. arXiv preprint arXiv:2406.10289. find
  41. Anupam Purwar and 1 others. 2024. Evaluating the efficacy of open-source llms in enterprise-specific rag systems: A comparative study of performance and scalability. arXiv preprint arXiv:2406.11424. — [arXiv:2406.11424](https://arxiv.org/abs/2406.11424) find
  42. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084.
  43. Wajiha Shahid, Bahman Jamshidi, Saqib Hakak, Haruna Isah, Wazir Zada Khan, Muhammad Khurram Khan, and Kim-Kwang Raymond Choo. 2022. Detecting and mitigating the dissemination of fake news: Challenges and future research opportunities. IEEE Transactions on Computational Social Systems, 11(4):4649–466… find
  44. 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
  45. Karen Sparck Jones. 1972. A statistical interpretation of term specificity and its application in retrieval. Journal of documentation, 28(1):11–21. find
  46. Jinyan Su, Claire Cardie, and Preslav Nakov. 2023. Adapting fake news detection to the era of large language models. arXiv preprint arXiv:2311.04917. find
  47. Hexiang Tan, Fei Sun, Wanli Yang, Yuanzhuo Wang, Qi Cao, and Xueqi Cheng. 2024. Blinded by generated contexts: How language models merge generated and retrieved contexts when knowledge conflicts? arXiv preprint arXiv:2401.11911.
  48. Qwen Team. 2025. Qwen3 technical report. Preprint, arXiv:2505.09388.
  49. Jacob-Junqi Tian, Hao Yu, Yury Orlovskiy, Tyler Vergho, Mauricio Rivera, Mayank Goel, Zachary Yang, Jean-Francois Godbout, Reihaneh Rabbany, and Kellin Pelrine. 2024. Web retrieval agents for evidence-based misinformation detection. arXiv preprint arXiv:2409.00009. — [arXiv:2409.00009](https://arxiv.org/abs/2409.00009) find
  50. Erik F. Tjong Kim Sang and Fien De Meulder. 2003. Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003, pages 142–147.
  51. Yue Wan, Xiaowei Jia, and Xiang Lorraine Li. 2025. Unveiling confirmation bias in chain-of-thought reasoning. arXiv preprint arXiv:2506.12301. find
  52. OpenAI. 2024. Gpt-4o-mini. https://platform.openai.com/docs/models. Accessed: 2024-10. ↗
  53. Keyu Wang, Jin Li, Shu Yang, Zhuoran Zhang, and Di Wang. 2025. When truth is overridden: Uncovering the internal origins of sycophancy in large language models. arXiv preprint arXiv:2508.02087. — [arXiv:2508.02087](https://arxiv.org/abs/2508.02087) find
  54. Bohdan M Pavlyshenko. 2023. Analysis of disinformation and fake news detection using fine-tuned large language model. arXiv preprint arXiv:2309.04704. — [arXiv:2309.04704](https://arxiv.org/abs/2309.04704) find
  55. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. Chain-of-thought prompting Xinyi Zhou and Reza Zafarani. 2020. A survey of fake news: Fundamental theories, detection methods, and opportunities. ACM Computing Surveys (CSUR), 53(5):1–… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wu-2026-zofia-zero-shot-fake-news/