AI hallucination: towards a comprehensive classification of distorted information in artificial intelligence-generated content
Open accessAbstract
Amidst the burgeoning information age, the rapid development of artificial intelligence-generated content (AIGC) has brought forth challenges regarding information authenticity. The proliferation of distorted information significantly impacts users negatively. This study aims to systematically categorize distorted information within AIGC, delve into its internal characteristics, and provide theoretical guidance for its management. Utilizing ChatGPT as a case study, we conducted empirical content analysis on 243 instances of distorted information collected, comprising both questions and answers. Three coders meticulously interpreted each instance of distorted information, encoding error points based on a predefined coding scheme and categorizing them according to error type. Our objective was to refine and validate the distorted information category list derived from the review through multiple rounds of pre-coding and test coding, thereby yielding a comprehensive and clearly delineated category list of distorted information in AIGC. The findings identified 8 first-level error types: “Overfitting”; “Logic errors”; “Reasoning errors”; “Mathematical errors”; “Unfounded fabrication”; “Factual errors”; “Text output errors”; and “Other errors”, further subdivided into 31 second-level error types. This classification list not only lays a solid foundation for studying risks associated with AIGC but also holds significant practical implications for helping users identify distorted information and enabling developers to enhance the quality of AI-generated tools.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
AI hallucinations encompass various forms of error, including factual inaccuracies, flawed logic, and fabricated content, which can easily mislead users lacking robust verification habits.
“As Sun and Colleagues (Sun et al. 2024) argue, AI hallucinations encompass various forms of error (including factual inaccuracies, flawed logic, and fabricated content) which can easily mislead users lacking robust verification habits.”
From Bridging risk and retention: risk coping with privacy and hallucination in AI (2026) · cites this paper as Sun et al. 2024
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The qualitative content analysis process
Elo, S., & Kyngäs, H. (2008) · Journal of Advanced Nursing · doi:10.1111/j.1365-2648.2007.04569.x · Cited by 22,617 · see citing works
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · cited 1× · see citing works
“Scholars have proposed various strategies to mitigate these issues, yet these approaches are not without their limitations (Ji et al. 2023).”
Content Analysis: A Flexible Methodology
White, M. D., & Marsh, E. (2006) · Library trends · doi:10.1353/lib.2006.0053 · Cited by 2,007 · see citing works
Prevalence of health misinformation on social media: systematic review
Suarez-Lledo, V., & Alvarez-Galvez, J. (2021) · Journal of Medical Internet Research · doi:10.2196/17187 · Cited by 1,564 · see citing works
A Brief Overview of ChatGPT: The History, Status Quo and Potential Future Development
Wu, T., He, S., Liu, J., Sun, S., Liu, K., Han, Q.-L., & Tang, Y. (2023) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2023.123618 · Cited by 1,452 · see citing works
A Survey of Fake News: Fundamental Theories, Detection Methods, and Opportunities
Zhou, X., & Zafarani, R. (2021) · ACM Computing Surveys · doi:10.1145/3395046 · Cited by 1,184 · see citing works
Kleinheksel, A. J., Rockich-Winston, N., Tawfik, H., & Wyatt, T. R. (2020) · American Journal of Pharmaceutical Education · doi:10.5688/ajpe7113 · Cited by 1,054 · see citing works
Social media and vaccine hesitancy
Wilson, S. L., & Wiysonge, C. S. (2020) · BMJ Global Health · doi:10.1136/bmjgh-2020-004206 · Cited by 978 · see citing works
A Categorical Archive of ChatGPT Failures
Borji, A. (2023) · doi:10.21203/rs.3.rs-2895792/v1 · Cited by 514 · see citing works
A Categorical Archive of ChatGPT Failures
Borji, A. (2023) · arXiv · doi:10.48550/arxiv.2302.03494 · Cited by 514 · see citing works
Fabrication and errors in the bibliographic citations generated by ChatGPT
Walters, W. H., & Wilder, E. I. (2023) · Scientific Reports · doi:10.1038/s41598-023-41032-5 · Cited by 499 · see citing works
Fake News Detection Using Machine Learning Ensemble Methods
Ahmad, I., Yousaf, M. M., Yousaf, S., & Ahmad, M. O. (2020) · Complexity · doi:10.1155/2020/8885861 · Cited by 488 · see citing works
Psychological inoculation improves resilience against misinformation on social media
Roozenbeek, J., van der Linden, S., Goldberg, B., Rathje, S., & Lewandowsky, S. (2022) · Science Advances · doi:10.1126/sciadv.abo6254 · Cited by 472 · see citing works
Brady, W. J., Crockett, M. J., & Van Bavel, J. J. (2020) · Perspectives on Psychological Science · doi:10.1177/1745691620917336 · Cited by 417 · see citing works
A Survey on ChatGPT: AI–Generated Contents, Challenges, and Solutions
Wang, Y., Pan, Y., Yan, M., Su, Z., & Luan, T. H. (2023) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2023.3300321 · Cited by 395 · see citing works
A systematic literature review on disinformation: Toward a unified taxonomical framework
Kapantai, E., Christopoulou, A., Berberidis, C., & Peristeras, V. (2020) · New Media & Society · doi:10.1177/1461444820959296 · Cited by 281 · see citing works
Rawte, V., Chakraborty, S., Pathak, A., et al. (2023) · Conference on Empirical Methods in Natural Language Processing · doi:10.48550/arxiv.2310.04988 · Cited by 262 · see citing works
Christensen, J., Hansen, J. M., & Wilson, P. (2024) · Current Issues in Tourism · doi:10.1080/13683500.2023.2300032 · Cited by 253 · see citing works
Artificial intelligence and increasing misinformation
Monteith, S., Glenn, T., Geddes, J. R., Whybrow, P. C., Achtyes, E., & Bauer, M. (2024) · The British Journal of Psychiatry · doi:10.1192/bjp.2023.136 · Cited by 208 · see citing works
Marketing with ChatGPT: Navigating the Ethical Terrain of GPT-Based Chatbot Technology
Rivas, P., & Zhao, L. (2023) · AI · doi:10.3390/ai4020019 · Cited by 191 · see citing works
Better by You, better than Me? ChatGPT-3 as writing assistance in students’ essays.
Bašić, Ž., Banovac, A., Kružić, I., & Jerković, I. (2023) · doi:10.35542/osf.io/n5m7s · Cited by 189 · see citing works
Li, W. (2025) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2024.2310354 · Cited by 167 · see citing works
Exploring ChatGPT Capabilities and Limitations: A Survey
Koubâa, A., Boulila, W., Ghouti, L., Alzahem, A., & Latif, S. (2023) · IEEE Access · doi:10.1109/access.2023.3326474 · Cited by 165 · see citing works
Quantitative Content Analysis: Its Use in Technical Communication
Boettger, R. K., & Palmer, L. A. (2010) · IEEE Transactions on Professional Communication · doi:10.1109/tpc.2010.2077450 · Cited by 128 · see citing works
A Mathematical Investigation of Hallucination and Creativity in GPT Models
Lee, M. (2023) · Mathematics · doi:10.3390/math11102320 · Cited by 105 · see citing works
Making sense of text: artificial intelligence-enabled content analysis
Lee, L. W., Dabirian, A., McCarthy, I. P., & Kietzmann, J. (2020) · European Journal of Marketing · doi:10.1108/ejm-02-2019-0219 · Cited by 103 · see citing works
The Web of False Information: Rumors, Fake News, Hoaxes, Clickbait, and Various Other Shenanigans
Zannettou, S., Sirivianos, M., Blackburn, J., & Kourtellis, N. (2019) · Journal of Data and Information Quality · doi:10.1145/3309699 · Cited by 86 · see citing works
Carrasco-Farré, C. (2022) · Humanities and Social Sciences Communications · doi:10.1057/s41599-022-01174-9 · Cited by 84 · see citing works
Cappellani, F., Card, K. R., Shields, C. L., Pulido, J. S., & Haller, J. A. (2024) · Eye · doi:10.1038/s41433-023-02906-0 · Cited by 74 · see citing works
Polyportis, A., & Pahos, N. (2024) · Humanities and Social Sciences Communications · doi:10.1057/s41599-023-02464-6 · Cited by 64 · see citing works
Artificial Hallucinations by Google Bard: Think Before You Leap
Kumar, M., Mani, U. A., Tripathi, P., Saalim, M., & Roy, S. (2023) · Cureus · doi:10.7759/cureus.43313 · Cited by 59 · see citing works
ChatGPT and the rise of semi-humans
Al Lily, A. E., Ismail, A. F., Abunaser, F. M., Al-Lami, F., & Abdullatif, A. K. A. (2023) · Humanities and Social Sciences Communications · doi:10.1057/s41599-023-02154-3 · Cited by 59 · see citing works
Performance of ChatGPT on registered nurse license exam in Taiwan: a descriptive study
Huang, H. (2023) · Healthcare · doi:10.3390/healthcare11212855 · Cited by 48 · see citing works
Artificial intelligence generated content (AIGC) in medicine: A narrative review
Shao, L., Chen, B., Zhang, Z., Zhang, Z., & Chen, X. (2024) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2024073 · Cited by 48 · see citing works
The European approach to online disinformation: geopolitical and regulatory dissonance
Casero-Ripollés, A., Navarro, J. T., & García, L. B. (2023) · Humanities and Social Sciences Communications · doi:10.1057/s41599-023-02179-8 · Cited by 42 · see citing works
A Survey on Hallucination in Large Vision-Language Models
Liu, H., Xue, W., Chen, Y., Chen, D., Zhao, X., Wang, K., Hou, L., Li, R., & Peng, W. (2024) · arXiv · doi:10.48550/arxiv.2402.00253 · Cited by 37 · see citing works
Automated vs Manual Content Analysis – A Retrospective Look
Anastasiei, I.-D., Georgescu, M. R., & Romania (2020) · Scientific Annals of Economics and Business · doi:10.47743/saeb-2020-0025 · Cited by 30 · see citing works
Future of disinformation studies: emerging research fields
Salaverría, R., & Cardoso, G. (2023) · El Profesional de la Informacion · doi:10.3145/epi.2023.sep.25 · Cited by 29 · see citing works
A value-driven approach to addressing misinformation in social media
Komendantova, N., Ekenberg, L., Svahn, M., Larsson, A., Shah, S. I. H., Glinos, M., Koulolias, V., & Danielson, M. (2021) · Humanities and Social Sciences Communications · doi:10.1057/s41599-020-00702-9 · Cited by 28 · see citing works
Beyond online disinformation: assessing national information resilience in four European countries
Dragomir, M., Araújo, J. R., & Horowitz, M. A. (2024) · Humanities and Social Sciences Communications · doi:10.1057/s41599-024-02605-5 · Cited by 26 · see citing works
Bastos, J. L., & Faerstein, E. (2012) · Cadernos de Saúde Pública · doi:10.1590/s0102-311x2012000100019 · Cited by 15 · see citing works
A Content Analysis of Adoption Articles in Counseling Journals: A 30-Year Review
Liu, Y., Jacoby, R. P., Jang, H., & Li, D. (2018) · The Family Journal · doi:10.1177/1066480718809424 · Cited by 15 · see citing works
Chen, M., Yu, W., & Liu, K. (2023) · Information Processing & Management · doi:10.1016/j.ipm.2023.103425 · Cited by 11 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- Mo Z, Pang D, Liu H, Zhao Y (2023) Analysis on AIGC False Information Problem and Root Cause from the Perspective of Information Quality. Doc- umentation,Inf Knowl 40(4):32-40. https://link.cnki.net/doi/10.13366/j.dik. 2023.04.032 · DOI
Cited by
Sorted by citations
Park, S., & Nan, X. (2026) · AI & SOCIETY · doi:10.1007/s00146-025-02620-3 · Cited by 58 · see citing works
“A major concern is hallucinations, where LLMs fabricate plausible but false information (Bandara 2024; Kamel 2024; Monteith et al. 2024; Sun et al. 2024).”
Song, Y., Cui, M., Wan, F., Yu, Z., & Jiang, J. (2025) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2025.2483858 · Cited by 30 · see citing works
Parker, L., Loper, A. J., Carter, C. W., Hayes, J., & Karakas, A. (2026) · Computers and Education Open · doi:10.1016/j.caeo.2025.100329 · Cited by 10 · see citing works
Lindkvist, A., Curbo, S., & Hultgren, C. (2026) · Frontiers in Education · doi:10.3389/feduc.2026.1813306 · Cited by 5 · see citing works
Chigwada, J., & Ngulube, P. (2026) · Frontiers in Research Metrics and Analytics · doi:10.3389/frma.2026.1740510 · Cited by 5 · see citing works
Learning-to-learn in the age of generative AI: a scoping review and conceptual framework
Schorr, I., Bardach, L., Bühler, B., & Kasneci, E. (2026) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2026.100575 · Cited by 3 · see citing works
McGrew, H. C., Faucett, K., Russell, R. G., Holt, J. E., Tapp, J., Steed, J., & Phillippi, J. (2025) · Journal of Midwifery & Women's Health · doi:10.1111/jmwh.70015 · Cited by 3 · see citing works
Bridging risk and retention: risk coping with privacy and hallucination in AI
Shin, D., Rasul, A., & Shahzad, K. (2026) · AI & SOCIETY · doi:10.1007/s00146-026-03127-1
“McDonald and Colleagues (McDonald et al. 2024) reported that nearly 60% of universities now include privacy advisories in their GAI usage guidelines, with many recommending that users refrain from submitting any per-sonally identifiable information.”
- Authors
- Sun, Y., Sheng, D., Zhou, Z., & Wu, Y.
- Affiliations
- Shandong Normal University (CN)
- Shandong University (CN)
- Corresponding author
- Sheng, Dongfang
- Venue
- Humanities and Social Sciences Communications
- Published
- 2024-09-27
- Volume
- 11
- Issue
- 1
- ISSN
- 2055-1045 (ISSN-L)
- 2662-9992
- OpenAlex
- W4402923059
- Cited by
- 327
- References
- 43
- Citations by year
- 2026: 189 · 2025: 130 · 2024: 8
- FWCI
- 233.78
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Humanities and Social Sciences Communications (publishedVersion, cc-by-nc-nd)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Office for Philosophy and Social Sciences
- Topics
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- AI hallucination, AI-generated content, error classification, ChatGPT, factual errors, reasoning errors, overfitting, mathematical errors, information authenticity, large language models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
