Elamur Research⌕
☰
home / papers / 2026 / KG-CRAFT: Knowledge Graph-based Contrastive Reasoning with LLMs for Enhancing Automated Fact-checking

KG-CRAFT: Knowledge Graph-based Contrastive Reasoning with LLMs for Enhancing Automated Fact-checking

Paper · 2026 · Vítor Lourenço, Aline Paes, Tillman Weyde et al.

Summary

KG-CRAFT addresses claim verification within automated fact-checking (AFC) in a bounded setting. Each claim comes with a fixed set of related reports, so the hard part is reasoning over the given material rather than retrieving evidence. The authors argue that LLM-based verifiers often lack structured reasoning, and that contrastive thinking (asking why one fact holds instead of a plausible alternative) is rarely used for this task.

Their pipeline works in three stages:

  1. An LLM, prompted few-shot in stages, extracts entities, labels their categories and connects them with relations. This produces a knowledge graph covering the claim and its reports.
  2. Contrastive questions are built by swapping the head or tail entity of each claim triple for another entity of the same category. A selection step favours questions that are relevant and diverse.
  3. The questions are answered from the reports, the answers are compressed into a short summary, and an LLM uses that summary to decide the claim's veracity.

On LIAR-RAW and RAWFC the method reports new state-of-the-art results. It also makes small language models competitive, which points toward cheaper fact-checking.

Key points

  • Datasets: LIAR-RAW and RAWFC. All experiments are English-only, although the method is meant to be language-agnostic.
  • Question template: "Why [original] rather than [alternative]?" The relation stays fixed, and the alternative entity shares the replaced entity's category in the graph.
  • Small models inside KG-CRAFT beat Naïve Claude 3.7 Sonnet (F1 62.22%):
    • SmolLM2 1.7B reaches an F1 of 73.40%.
    • Qwen3 0.6B reaches an F1 of 66.34%.
  • Using more contrastive questions improves results, but even a small number gives competitive performance.
  • Stated limitations:
    • The knowledge graph step and other intermediate outputs are not checked qualitatively.
    • The pipeline depends on costly LLMs.
    • Baselines use different LLM families, which threatens a fair comparison.

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

🎓Universidade Federal FluminenseNiterói · Brazil2 works · 374 citations🎓City St George's, University of LondonLondon · United Kingdom2 works · 6 citations

 Fields, topics and concepts

📚 Shelves 6The 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 worksSociology and Political Science · 577 works

🧭 Topics 2Research subjects and languages the work is about.Reasoning · 1,426 worksKnowledge graphs & ontologies · 192 works

Cite

Cite as Vítor Lourenço, Aline Paes, Tillman Weyde, Audrey Depeige and Mohnish Dubey. 2026. KG-CRAFT: Knowledge Graph-based Contrastive Reasoning with LLMs for Enhancing Automated Fact-checking. Proceedings of the 19th Conference of the European Chapter 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.eacl-long.302

@inproceedings{lourenco2026kg,
  title = {{KG-CRAFT: Knowledge Graph-based Contrastive Reasoning with LLMs for Enhancing Automated Fact-checking}},
  author = {Vítor Lourenço, Aline Paes, Tillman Weyde, Audrey Depeige and Mohnish Dubey},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-long.302},
  url = {https://doi.org/10.18653/v1/2026.eacl-long.302}
}

References

66 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Firoj Alam, Stefano Cresci, Tanmoy Chakraborty, Fabrizio Silvestri, Dimiter Dimitrov, Giovanni Da San Martino, Shaden Shaar, Hamed Firooz, and Preslav Nakov. 2022. A survey on multimodal disinformation detection. In Proc. 29th Int. Conf. Comput. Linguist., COLING. find
  2. Tariq Alhindi, Savvas Petridis, and Smaranda Muresan. 2018. Where is your evidence: Improving fact-checking by justification modeling. In Proceedings of the First Workshop on Fact Extraction and VERification (FEVER). Association for Computational Linguistics.
  3. Loubna Ben Allal, Anton Lozhkov, Elie Bakouch, Gabriel Martín Blázquez, Guilherme Penedo, Lewis Tunstall, Andrés Marafioti, Hynek Kydlíček, Agustín Piqueres Lajarín, Vaibhav Srivastav, Joshua Lochner, Caleb Fahlgren, Xuan-Son Nguyen, Clémentine Fourrier, Ben Burtenshaw, Hugo Larcher, Haojun Zhao, Cy… — SmolLM2: When Smol Goes Big — Data-Centric Training of a Small Language Model
  4. Rami Aly, Zhijiang Guo, Michael Sejr Schlichtkrull, James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Oana Cocarascu, and Arpit Mittal. 2021. The fact extraction and VERification over unstructured and structured information (FEVEROUS) shared task. In Proceedings of the Fourth Workshop on F…
  5. 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.
  6. Isabelle Augenstein, Timothy Baldwin, Meeyoung Cha, Tanmoy Chakraborty, Giovanni Luca Ciampaglia, David Corney, Renee DiResta, Emilio Ferrara, Scott Hale, Alon Halevy, Eduard Hovy, Heng Ji, Filippo Menczer, Ruben Miguez, Preslav Nakov, Dietram Scheufele, Shivam Sharma, and Giovanni Zagni. 2024. Fact… — Factuality Challenges in the Era of Large Language Models
  7. Amrita Bhattacharjee, Mansooreh Karami, and Huan Liu. 2022. Text transformations in contrastive self-supervised learning: A review. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23-29 July 2022, pages 5394–5401. ijcai.org. find
  8. Zana Buçinca, Siddharth Swaroop, Amanda E. Paluch, Finale Doshi-Velez, and Krzysztof Z. Gajos. 2025. Contrastive explanations that anticipate human misconceptions can improve human decision-making skills. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, CHI 2025, Yoko… find
  9. Bohan Chen and Andrea L Bertozzi. 2023. Autokg: Efficient automated knowledge graph generation for language models. In 2023 IEEE International Conference on Big Data (BigData), pages 3117–3126. IEEE. find
  10. Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In Proceedings of ICML.
  11. Yingjian Chen, Haoran Liu, Yinhong Liu, Jinxiang Xie, Rui Yang, Han Yuan, Yanran Fu, Peng Yuan Zhou, Qingyu Chen, James Caverlee, and Irene Li. 2025. GraphCheck: Breaking long-term text barriers with extracted knowledge graph-powered fact-checking. In Proceedings of the 63rd Annual Meeting of the As… find
  12. Tsun-Hin Cheung and Kin-Man Lam. 2023. Factllama: Optimizing instruction-following language models with external knowledge for automated fact-checking. In 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference. find
  13. Islam Eldifrawi, wi, 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. find
  14. Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. Simcse: Simple contrastive learning of sentence embeddings. In Proceedings of EMNLP.
  15. Riccardo Guidotti. 2024. Counterfactual explanations and how to find them: literature review and benchmarking. Data Mining and Knowledge Discovery, 38(5):2770–2824. find
  16. Hao Guo, Weixin Zeng, Jiuyang Tang, and Xiang Zhao. 2023. Interpretable fake news detection with graph evidence. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. find
  17. Zhijiang Guo, M. Schlichtkrull, and Andreas Vlachos. 2021. A survey on automated fact-checking. Transactions of the Association for Computational Linguistics, 10:178–206.
  18. Jutta Haider and Olof Sundin. 2022. Paradoxes of media and information literacy: The crisis of information. Taylor & Francis. find
  19. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations.
  20. Yani Huang, Richong Zhang, Zhijie Nie, Junfan Chen, and Xuefeng Zhang. 2025. A graph-based verification framework for fact-checking. Preprint, arXiv:2503.07282. — [arXiv:2503.07282](https://arxiv.org/abs/2503.07282) find
  21. Alon Jacovi, Swabha Swayamdipta, Shauli Ravfogel, Yanai Elazar, Yejin Choi, and Yoav Goldberg. 2021. Contrastive explanations for model interpretability. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. find
  22. Neema Kotonya and Francesca Toni. 2020. Explainable automated fact-checking for public health claims. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.
  23. Canasai Kruengkrai, Junichi Yamagishi, and Xin Wang. 2021. A multi-level attention model for evidence-based fact checking. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2447– 2460, Online. Association for Computational Linguistics. find
  24. Yuqing Lan, Zhenghao Liu, Yu Gu, Xiaoyuan Yi, Xiaohua Li, Liner Yang, and Ge Yu. 2025. Multi-Evidence Based Fact Verification via A Confidential Graph Neural Network . IEEE Transactions on Big Data, 11(02):426– 437. find
  25. Peter Lipton. 1990. Contrastive explanation. Royal Institute of Philosophy Supplements, 27:247–266. find
  26. Hui Liu, Wenya Wang, Haoru Li, and Haoliang Li. 2024. Teller: A trustworthy framework for explainable, generalizable and controllable fake news detection. In Findings of the Association for Computational Linguistics: ACL 2024. find
  27. Zhibin Liu, Zheng-Yu Niu, Hua Wu, and Haifeng Wang. 2019. Knowledge aware conversation generation with explainable reasoning over augmented graphs. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language… find
  28. Vítor Lourenço, Aline Paes, and Tillman Weyde. 2025. Exploring content and social connections of fake news with explainable text and graph learning. In Proceedings of the XXXV Brazilian Conference on Intelligent Systems (to appear). SBC. find
  29. Vítor Lourenço and Aline Paes. 2022. A modality-level explainable framework for misinformation checking in social networks. In LatinX AI Workshop at 36th Conf. Neural Inf. Process. Syst., LXAI-NeurIPS. find
  30. Mark Huasong Meng, Ruizhe Wang, Meng Xu, Chuan Yan, and Guangdong Bai. 2025. Detecting manipulated contents using knowledge-grounded inference. find
  31. Tim Miller. 2019. Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267.
  32. Alireza Mohammadshahi, Thomas Scialom, Majid Yazdani, Pouya Yanki, Angela Fan, James Henderson, and Marzieh Saeidi. 2023. RQUGE: Reference-free metric for evaluating question generation by answering the question. In Findings of the Association for Computational Linguistics: ACL 2023. find
  33. American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). find
  34. Nic Newman, Richard Fletcher, Craig T. Robertson, Amy Ross Arguedas, and Rasmus Kleis Nielsen. 2024. Reuters institute digital news report 2024. Technical report, Reuters Institute for the Study of Journalism. find
  35. Sebastián Valenzuela, Daniel Halpern, James E Katz, and Juan Pablo Miranda. 2019. The paradox of participation versus misinformation: Social media, political engagement, and the spread of misinformation. Digital Journalism, 7(6):802–823. find
  36. Liangming Pan, Xiaobao Wu, Xinyuan Lu, Anh Tuan Luu, William Yang Wang, Min-Yen Kan, and Preslav Nakov. 2023. Fact-checking complex claims with program-guided reasoning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6981–700…
  37. Shirui Pan, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, and Xindong Wu. 2024. Unifying large language models and knowledge graphs: A roadmap. IEEE Transactions on Knowledge and Data Engineering, 36(7):3580–3599.
  38. Bhargavi Paranjape, Julian Michael, Marjan Ghazvininejad, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2021. Prompting contrastive explanations for commonsense reasoning tasks. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. find
  39. Umair Qudus, Michael Röder, Muhammad Saleem, and Axel-Cyrille Ngonga Ngomo. 2025. Fact checking knowledge graphs – a survey. ACM Comput. Surv. find
  40. Tal Schuster, Adam Fisch, and Regina Barzilay. 2021. Get your vitamin c! robust fact verification with contrastive evidence. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, June…
  41. Kai Shu, Limeng Cui, Suhang Wang, Dongwon Lee, and Huan Liu. 2019. defend: Explainable fake news detection. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. find
  42. Ronit Singal, Pransh Patwa, Parth Patwa, Aman Chadha, and Amitava Das. 2024. Evidence-backed fact checking using RAG and few-shot in-context learning with LLMs. In Proceedings of the Seventh Fact Extraction and VERification Workshop. find
  43. Ilia Stepin, Jose M. Alonso, Alejandro Catala, and Martín Pereira-Fariña. 2021. A survey of contrastive and counterfactual explanation generation methods for explainable artificial intelligence. IEEE Access, 9. find
  44. Xin Tan, Bowei Zou, and Ai Ti Aw. 2025. Improving explainable fact-checking with claim-evidence correlations. In Proceedings of the 31st International Conference on Computational Linguistics. find
  45. James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and VERification. In Proceedings of the 2018 Conference of the North Sahil Verma, Varich Boonsanong, Minh Hoang, Keegan Hines, John Dickerson, and Chirag Shah. 2024. C…
  46. David Wadden, Shanchuan Lin, Kyle Lo, Lucy Lu Wang, Madeleine van Zuylen, Arman Cohan, and Hannaneh Hajishirzi. 2020. Fact or fiction: Verifying scientific claims. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7534–7550.
  47. David Wadden, Kyle Lo, Lucy Lu Wang, Arman Cohan, Iz Beltagy, and Hannaneh Hajishirzi. 2022. MultiVerS: Improving scientific claim verification with weak supervision and full-document context. In Findings of the Association for Computational Linguistics: NAACL 2022. find
  48. Bo Wang, Jing Ma, Hongzhan Lin, Zhiwei Yang, Ruichao Yang, Yuan Tian, and Yi Chang. 2024a. Explainable fake news detection with large language model via defense among competing wisdom. In Proceedings of the ACM Web Conference 2024. find
  49. Jinguang Wang, Shengsheng Qian, Jun Hu, Wenxiang Dong, Xudong Huang, and Richang Hong. 2025. End-to-end explainable fake news detection via evidence-claim variational causal inference. ACM Trans. Inf. Syst., 43(4). find
  50. Yuxia Wang, Minghan Wang, Muhammad Arslan Manzoor, Fei Liu, Georgi Nenkov Georgiev, Rocktim Jyoti Das, and Preslav Nakov. 2024b. Factuality of large language models: A survey. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 19519–19529, Miami, Florida…
  51. Chenxi Whitehouse, Tillman Weyde, Pranava Madhyastha, and Nikos Komninos. 2022. Evaluation of fake news detection with knowledge-enhanced language models. Proceedings of the International AAAI Conference on Web and Social Media, 16(1). find
  52. Zhouhui Wu, Nan Sun, Jiaojiao Jiang, and Shuiqiao Yang. 2025. Systematic approaches to fact verification: Evidence retrieval, veracity prediction, and beyond. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, pages 271–289. Springer. find
  53. Zhuohan Xie, Rui Xing, Yuxia Wang, Jiahui Geng, Hasan Iqbal, Dhruv Sahnan, Iryna Gurevych, and Preslav Nakov. 2025. Fire: Fact-checking with iterative retrieval and verification. In Findings of the Association for Computational Linguistics: NAACL 2025. find
  54. Cheng Xiong, Gengfeng Zheng, Xiao Ma, Chunlin Li, and Jiangfeng Zeng. 2025. Delphiagent: A trustworthy multi-agent verification framework for automated fact verification. Information Processing & Management, 62(6):104241. find
  55. 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, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. Qwen3 technical report. Preprint, arXiv:2505.09388.
  56. Seng Chua. 2021. TAT-QA: A question answering benchmark on a hybrid of tabular and textual content in finance. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)…
  57. Yuqi Zhu, Xiaohan Wang, Jing Chen, Shuofei Qiao, Yixin Ou, Yunzhi Yao, Shumin Deng, Huajun Chen, and Ningyu Zhang. 2024. Llms for knowledge graph construction and reasoning: Recent capabilities and future opportunities. World Wide Web, 27(5):58. find
  58. 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. find
  59. Zhenrui Yue, Huimin Zeng, Lanyu Shang, Yifan Liu, Yang Zhang, and Dong Wang. 2024. Retrieval augmented fact verification by synthesizing contrastive arguments. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. find
  60. Yuheng Zha, Yichi Yang, Ruichen Li, and Zhiting Hu. 2023. AlignScore: Evaluating factual consistency with a unified alignment function. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
  61. Bowen Zhang and Harold Soh. 2024. Extract, define, canonicalize: An llm-based framework for knowledge graph construction. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 9820–9836.
  62. Xuan Zhang and Wei Gao. 2024. Reinforcement retrieval leveraging fine-grained feedback for fact checking news claims with black-box LLM. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. find
  63. Xiaoyan Zhao, Lingzhi Wang, Zhanghao Wang, Hong Cheng, Rui Zhang, and Kam-Fai Wong. 2024. PACAR: Automated fact-checking with planning and customized action reasoning using large language models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resourc… find
  64. Lucia Zheng, Neel Guha, Brandon R. Anderson, Peter Henderson, and Daniel E. Ho. 2021. When does pre-training help? assessing self-supervised learning for law and the casehold dataset of 53,000+ legal holdings. In Proceedings of the Eighteenth International Conference on Artificial Intelligence and L… find
  65. Xinyi Zhou and Reza Zafarani. 2020. A survey of fake news: Fundamental theories, detection methods, and opportunities. ACM Comput. Surv., 53(5). find
  66. Fengbin Zhu, Wenqiang Lei, Youcheng Huang, Chao Wang, Shuo Zhang, Jiancheng Lv, Fuli Feng, and Tat- find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/lourenco-2026-kg-craft-knowledge-graph-based/