Elamur Research⌕
☰
home / papers / 2026 / FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs

FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs

Paper · 2026 · Albert Sawczyn, Jakub Binkowski, Denis Janiak et al.

Summary

LLMs often produce false statements, and most existing detectors only mark whole passages or sentences as suspect. They do not show which specific claim is wrong. The authors propose FactSelfCheck, a black-box, zero-resource, sampling-based detector that works at the level of individual facts, each represented as a knowledge-graph triple (head, relation, tail).

A chain of LLM prompts first extracts entities, then relations, then triples from the original response and from several stochastically sampled responses. Each fact's hallucination score reflects how consistently the samples support it. FactSelfCheck-KG compares the fact against the samples' graphs, while FactSelfCheck-Text compares it against the raw sample text. Fact scores can also be aggregated into sentence scores.

The method was evaluated on the WikiBio GPT-3 Hallucination Dataset and on the new FavaMultiSamples benchmark. At sentence level it is competitive with leading sampling-based methods, and at fact level it clearly beats them. Passing the detected wrong facts to a correction step substantially raises factual content. This makes the approach useful for interpretable, training-free verification of any LLM, including closed ones.

Key points

  • On fact-level detection (WikiBio, AUC-PR), FactSelfCheck-Text scores 93.41 and FactSelfCheck-KG (LLM-based) scores 92.25. A frequency-based variant reaches 87.99 and SelfCheckGPT (Prompt) reaches 86.18.
  • In hallucination correction, the share of factual sentences rises from a 0.23 baseline to 0.31 with fact-level feedback (+35.5%). Sentence-level SelfCheckGPT feedback reaches only 0.25 (+10.6%). Non-factual sentences drop from 0.74 to 0.64.
  • Refusals stay low, rising only from 0.04 to 0.05.
  • The new FavaMultiSamples dataset is only the second benchmark for sampling-based detectors. It is released on Hugging Face under CC BY-SA 4.0, and the code is on GitHub (graphml-lab-pwr).
  • The method needs no tuned hyperparameters or external knowledge. Its main limitations are:
    • higher compute cost from multiple LLM steps;
    • evaluation only via sentence-level annotations, since no long-form fact-annotated data exists.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 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

Cite

Cite as Albert Sawczyn, Jakub Binkowski, Denis Janiak, Bogdan Gabrys and Tomasz Jan Kajdanowicz. 2026. FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs. Findings of the Association for Computational Linguistics: EACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-eacl.296

@inproceedings{sawczyn2026factselfcheck,
  title = {{FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs}},
  author = {Albert Sawczyn, Jakub Binkowski, Denis Janiak, Bogdan Gabrys and Tomasz Jan Kajdanowicz},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.296},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.296}
}

References

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

  1. Amos Azaria and Tom Mitchell. 2023. The internal state of an LLM knows when it‘s lying. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 967–976, Singapore. Association for Computational Linguistics.
  2. Harrison Chase. 2022. Langchain. find
  3. Chao Chen, Kai Liu, Ze Chen, Yi Gu, Yue Wu, Mingyuan Tao, Zhihang Fu, and Jieping Ye. 2024. Inside: Llms’ internal states retain the power of hallucination detection. Preprint, arXiv:2402.03744.
  4. I-Chun Chern, Steffi Chern, Shiqi Chen, Weizhe Yuan, Kehua Feng, Chunting Zhou, Junxian He, Graham Neubig, and Pengfei Liu. 2023. Factool: Factuality detection in generative ai – a tool augmented framework for multi-task and multi-domain scenarios. Preprint, arXiv:2307.13528.
  5. Yung-Sung Chuang, Linlu Qiu, Cheng-Yu Hsieh, Ranjay Krishna, Yoon Kim, and James R. Glass. 2024. Lookback lens: Detecting and mitigating contextual hallucinations in large language models using only attention maps. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Proces…
  6. Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, and Jason Weston. 2024. Chain-of-verification reduces hallucination in large language models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 3563–3578, Bangkok, Thailand. Associ…
  7. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization. Preprint, arXiv:2404.16130. find
  8. Xinyue Fang, Zhen Huang, Zhiliang Tian, Minghui Fang, Ziyi Pan, Quntian Fang, Zhihua Wen, Hengyue Pan, and Dongsheng Li. 2024. Zero-resource hallucination detection for text generation via graph-based contextual knowledge triples modeling. arXiv preprint arXiv:2409.11283. — [arXiv:2409.11283](https://arxiv.org/abs/2409.11283) find
  9. Sebastian Farquhar, Jannik Kossen, Lorenz Kuhn, and Yarin Gal. 2024. Detecting hallucinations in large language models using semantic entropy. Nature, 630(8017):625–630. Publisher: Nature Publishing Group. find
  10. Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, and Nanyun Peng. 2024. LLM self-correction with De-CRIM: Decompose, critique, and refine for enhanced following of instructions with multiple constraints.… find
  11. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 o… — The Llama 3 Herd of Models
  12. William L. Hamilton, Rex Ying, and Jure Leskovec. 2017. Representation learning on graphs: Methods and applications. In IEEE Data Eng. Bull., volume 40, pages 52–74. find
  13. Xiangkun Hu, Dongyu Ru, Lin Qiu, Qipeng Guo, Tianhang Zhang, Yang Xu, Yun Luo, Pengfei Liu, Yue Zhang, and Zheng Zhang. 2024. Knowledge-centric hallucination detection. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 6953–6975, Miami, Florida, USA. As… find
  14. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2025. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Trans. Inf. Syst., 43(2).
  15. Denis Janiak, Jakub Binkowski, Albert Sawczyn, Bogdan Gabrys, Ravid Shwartz-Ziv, and Tomasz Kajdanowicz. 2025. The illusion of progress: Re-evaluating hallucination detection in llms. Preprint, arXiv:2508.08285. find
  16. Saurav Kadavath, Tom Conerly, Amanda Askell, Tom Henighan, Dawn Drain, Ethan Perez, Nicholas Schiefer, Zac Hatfield-Dodds, Nova DasSarma, Eli Tran-Johnson, Scott Johnston, Sheer El-Showk, Andy Jones, Nelson Elhage, Tristan Hume, Anna Chen, Yuntao Bai, Sam Bowman, Stanislav Fort, and 17 others. 2022.… find
  17. Jannik Kossen, Jiatong Han, Muhammed Razzak, Lisa Schut, Shreshth Malik, and Yarin Gal. 2024. Semantic entropy probes: Robust and cheap hallucination detection in llms. Preprint, arXiv:2406.15927. — [arXiv:2406.15927](https://arxiv.org/abs/2406.15927) find
  18. Ruslan Kuprieiev, skshetry, Peter Rowlands, Dmitry Petrov, Paweł Redzyński, Casper da Costa-Luis, David de la Iglesia Castro, Alexander Schepanovski, Ivan Shcheklein, Gao, Batuhan Taskaya, Jorge Orpinel, Fábio Santos, Daniele, Ronan Lamy, Aman Sharma, Zhanibek Kaimuldenov, Dani Hodovic, Nikita Kode… find
  19. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient memory management for large language model serving with pagedattention. In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
  20. Minhyeok Lee. 2023. A mathematical investigation of hallucination and creativity in gpt models. Mathematics, 11(10). find
  21. Quentin Lhoest, Albert Villanova del Moral, Yacine Jernite, Abhishek Thakur, Patrick von Platen, Suraj Patil, Julien Chaumond, Mariama Drame, Julien Plu, Lewis Tunstall, Joe Davison, Mario Šaško, Gunjan Chhablani, Bhavitvya Malik, Simon Brandeis, Teven Le Scao, Victor Sanh, Canwen Xu, Nicolas Patry,… — Datasets: A Community Library for Natural Language Processing
  22. Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics.
  23. Zicheng Lin, Zhibin Gou, Tian Liang, Ruilin Luo, Haowei Liu, and Yujiu Yang. 2024. CriticBench: Benchmarking LLMs for critique-correct reasoning. In Findings of the Association for Computational Linguistics: ACL 2024, pages 1552–1587, Bangkok, Thailand. Association for Computational Linguistics. find
  24. Potsawee Manakul, Adian Liusie, and Mark Gales. 2023. SelfCheckGPT: Zero-resource black-box hallucination detection for generative large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9004–9017, Singapore. Association for Computation… find
  25. Ning Miao, Yee Whye Teh, and Tom Rainforth. 2023. Selfcheck: Using llms to zero-shot check their own step-by-step reasoning. Preprint, arXiv:2308.00436.
  26. Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2023. FActScore: Fine-grained atomic evaluation of factual precision in long form text generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural L…
  27. Abhika Mishra, Akari Asai, Vidhisha Balachandran, Yizhong Wang, Graham Neubig, Yulia Tsvetkov, and Hannaneh Hajishirzi. 2024. Fine-grained hallucinations detections. arXiv preprint. find
  28. OpenAI, :, Aaron Hurst, Adam Lerer, Adam P. Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, Aleksander M adry, Alex Baker-Whitcomb, Alex Beutel, Alex Borzunov, Alex Carney, Alex Chow, Alex Kirillov, and 401 others. 2024. Gpt-4o system card.…
  29. Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, and William Yang Wang. 2024. Automatically correcting large language models: Surveying the landscape of diverse automated correction strategies. Transactions of the Association for Computational Linguistics, 12:484–506.
  30. Mohamed Rashad, Ahmed Zahran, Abanoub Amin, Amr Abdelaal, and Mohamed Altantawy. 2024. FactAlign: Fact-level hallucination detection and classification through knowledge graph alignment. In Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024), pages 79–84, Mexic… find
  31. Malik Sallam. 2023. Chatgpt utility in healthcare education, research, and practice: Systematic review on the promising perspectives and valid concerns. Healthcare, 11(6). find
  32. Hannah Sansford, Nicholas Richardson, Hermina Petric Maretic, and Juba Nait Saada. 2024. Grapheval: A knowledge-graph based llm hallucination evaluation framework. Preprint, arXiv:2407.10793. — [arXiv:2407.10793](https://arxiv.org/abs/2407.10793) find
  33. Gaurang Sriramanan, Siddhant Bharti, Vinu Sankar Sadasivan, Shoumik Saha, Priyatham Kattakinda, and Soheil Feizi. 2024. LLM-check: Investigating detection of hallucinations in large language models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. on Learning Represen… find
  34. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, and 3 others. 2020. Transf…
  35. Ziwei Xu, Sanjay Jain, and Mohan Kankanhalli. 2024. Hallucination is inevitable: An innate limitation of large language models. Preprint, arXiv:2401.11817.
  36. Muru Zhang, Ofir Press, William Merrill, Alisa Liu, and Noah A. Smith. 2024a. How language model hallucinations can snowball. In Proceedings of the 41st International Conference on Machine Learning, ICML’24. JMLR.org.
  37. Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou, Lifeng Jin, Linfeng Song, Haitao Mi, and Helen Meng. 2024b. Self-alignment for factuality: Mitigating hallucinations in LLMs via self-evaluation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1:…
  38. Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, Longyue Wang, Anh Tuan Luu, Wei Bi, Freda Shi, and Shuming Shi. 2023. Siren’s song in the ai ocean: A survey on hallucination in large language models. Preprint, arXiv:2309.01219.
  39. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. In Proceedings of the 37th International Conference on Neu…
  40. Aman Singh Thakur, Kartik Choudhary, Venkat Srinik Ramayapally, Sankaran Vaidyanathan, and Dieuwke Hupkes. 2025. Judging the judges: Evaluating alignment and vulnerabilities in llms-as-judges. Preprint, arXiv:2406.12624. find
  41. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/sawczyn-2026-factselfcheck-fact-level-black-box/