M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection
Open accessAbstract
Yuxia Wang, Jonibek Mansurov, Petar Ivanov, Jinyan Su, Artem Shelmanov, Akim Tsvigun, Osama Mohammed Afzal, Tarek Mahmoud, Giovanni Puccetti, Thomas Arnold, Alham Aji, Nizar Habash, Iryna Gurevych, Preslav Nakov. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
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?
One variation of the human-LLM co-authored text attribution task is to detect the boundary between human-written and LLM-generated text.
“One variation of this task is to detect the boundary between human-written and LLM-generated text [Cutler et al., 2021;Wang et al., 2024].”
From Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges (2025) · cites this paper as Wang et al., 2024
Some studies have formulated a seven-class classification that includes one human class and six LLM classes.
“Some studies have formulated a seven-class classification that includes one human class and six LLM classes [He et al., 2023;Wang et al., 2024].”
From Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges (2025) · cites this paper as Wang et al., 2024
Advanced techniques are required to dissect these integrations, identifying where and how the contributions of LLM intersect with human input.
“Advanced techniques are required to dissect these integrations, identifying where and how the contributions of LLM intersect with human input [Wang et al., 2024].”
From Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges (2025) · cites this paper as Wang 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 publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 4
- Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2021. Deberta: decoding-enhanced bert with disentangled attention. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenRe- view.net.
- Jenny S Li, John V Monaco, Li-Chiou Chen, and Charles C Tappert. 2014. Authorship authentica- tion using short messages from social networking sites. In 2014 IEEE 11th International Conference on e-Business Engineering, pages 314-319. IEEE.
- Rafael Rivera Soto, Kailin Koch, Aleem Khan, Barry Chen, Marcus Bishop, and Nicholas Andrews. 2024. Few-shot detection of machine-generated text using style representations. arXiv e-prints, pages arXiv- 2401.
- Rowan Zellers, Ari Holtzman, Hannah Rashkin, Yonatan Bisk, Ali Farhadi, Franziska Roesner, and Yejin Choi. 2019. Defending against neural fake news. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Informa- tion Processing Systems 2019, NeurIPS 2019, De- cember 8-14, 2019, Vancouver, BC, Canada, pages 9051-9062.
Cited by
Sorted by citations
Factuality challenges in the era of large language models and opportunities for fact-checking
Augenstein, I., Baldwin, T., Cha, M., Chakraborty, T., Ciampaglia, G. L., Corney, D., DiResta, R., Ferrara, E., Hale, S., Halevy, A., et al. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00881-z · Cited by 187 · see citing works
Self-citationPudasaini, S., Miralles-Pechuán, L., Lillis, D., & Llorens Salvador, M. (2025) · Journal of Academic Ethics · doi:10.1007/s10805-024-09576-x · Cited by 70 · see citing works
Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges
Huang, B., Chen, C., & Shu, K. (2025) · ACM SIGKDD Explorations Newsletter · doi:10.1145/3715073.3715076 · Cited by 42 · see citing works
Srba, I., Razuvayevskaya, O., Leite, J. A., Moro, R., Schlicht, I. B., Tonelli, S., García, F. M., Lottmann, S. B., Teyssou, D., Porcellini, V., et al. (2026) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3770077 · Cited by 19 · see citing works
Yang, Z., Feng, Z., Huo, R., Lin, H., Zheng, H., Nie, R., & Chen, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126694 · Cited by 17 · see citing works
Advancements in AI-Generated Content Forensics: A Systematic Literature Review
Xu, Q., Mu, W., Li, J., Sun, T., & Jiang, X. (2025) · ACM Computing Surveys · doi:10.1145/3760526 · Cited by 16 · see citing works
MultiSocial: Multilingual Benchmark of Machine-Generated Text Detection of Social-Media Texts
Macko, D., Kopál, J., Móro, R., & Srba, I. (2025) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2025.acl-long.36 · Cited by 13 · see citing works
Wang, Q., & Li, H. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9030050 · Cited by 12 · see citing works
A Large Language Model-based Fake News Detection Framework with RAG Fact-Checking
Bai, Y., & Fu, K. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10826000 · Cited by 11 · see citing works
Enhancing the Robustness of AI-Generated Text Detectors: A Survey
Liu, X., Li, Y., & Li, K. (2025) · Mathematics · doi:10.3390/math13132145 · Cited by 10 · see citing works
CoAT: Corpus of artificial texts
Shamardina, T., Saidov, M., Fenogenova, A., Tumanov, A., Zemlyakova, A., Lebedeva, A., Gryaznova, E., Shavrina, T., Mikhailov, V., & Artemova, E. (2024) · Natural language processing. · doi:10.1017/nlp.2024.38 · Cited by 8 · see citing works
Bevendorff, J., Dementieva, D., Fröbe, M., Gipp, B., Greiner-Petter, A., Jussi Karlgren, C., Mayerl, M., Nakov, P., Panchenko, A., Potthast, M., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88720-8_64 · Cited by 5 · see citing works
Self-citationDefending mutation-based adversarial text perturbation: a black-box approach
Deanda, D., Alsmadi, I. M., Guerrero, J., & Liang, G. (2025) · Cluster Computing · doi:10.1007/s10586-024-04916-3 · Cited by 4 · see citing works
Beyond N-Grams: Enhancing String Kernels With Transformer-Guided Semantic Insights
Zaki, N., Alderei, R., Alketbi, M., Alkaabi, A., Alneyadi, F., & Zaki, N. (2025) · IEEE Access · doi:10.1109/access.2025.3576076 · Cited by 4 · see citing works
On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writing
Liu, Y., Zhong, Z., Liao, Y., Sun, Z. T., Zheng, J., Wei, J., Gong, Q., Tong, F., Chen, Y., Zhang, Y., et al. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737408 · Cited by 4 · see citing works
Arabic machine-generated text detection: Stylometric analysis and cross-model evaluation
Al-shaibani, M. S., & Ahmed, M. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130644 · Cited by 2 · see citing works
Puspo, S. S. C., Raihan, N., Goswami, D., Emran, A. N. B., Ganguly, A., & Uzuner, Ö. (2024) · International Workshop on Semantic Evaluation (SemEval) · doi:10.18653/v1/2024.semeval-1.197
Detecting Large Language Model Generated Korean Essays Using Curriculum LearningPreprint
Jung, Y., & Oh, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5380275
Evaluating Fine-Tuned LLMs for AI Text Detection
Murgia, M., Recupero, D. R., & Spathoulas, G. P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-00642-4_17
Creating Frameworks and Datasets at the Intersection of AI Safety and Elections
Dmonte, A., Wang, Y., Nakov, P., Li, H., Han, X., Zampieri, M., Lybarger, K., Albanese, M., & Baldwin, T. (2025) · Springer eBooks · doi:10.1007/978-3-031-89853-2_9
Self-citationMixture of Detectors: A Compact View of Machine-Generated Text DetectionPreprint
Teja, L. S., Yadagiri, A., Challa, A. K., Machireddy, S. R., Pakray, P., & Chunka, C. (2025) · Research Square · doi:10.21203/rs.3.rs-7426641/v1
Dingfelder, P., & Rieß, C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-10759-6_16
LIN, X., & Ma, H. (2025) · Research Square · doi:10.21203/rs.3.rs-7638610/v1
A Comprehensive Survey of Machine-Generated Text Detection
孙, 一. (2025) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2026.151005
A Systematic Review of AI-Generated Text Detection: Approaches, Tools, and Datasets
Alethary, A. A., & Aliwy, A. H. (2026) · Al-Salam Journal for Engineering and Technology · doi:10.55145/ajest.2026.05.01.012
AI-Generated Text Detector for Arabic Language: Survey and Remarks
Salem, H., Elkhateb, A. G., Zafar, M. N., Mazzara, M., Al-Atyat, Y. K., & Hattab, S. (2026) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-032-23341-7_16
Curan, K. (2026) · Research Square · doi:10.21203/rs.3.rs-10448398/v1
Combining probabilistic features and semantic features for AI-Generated text detection
Yu, Y., & Gao, W. (2026) · International Journal of Scientific Research and Management (IJSRM) · doi:10.18535/ijsrm/v14i09.ec01
Alshammari, B. S., Alfraidi, K. N., Aljudaiey, M. O., & Abdelhalim, W. (2026) · Scientific Reports · doi:10.1038/s41598-026-67331-1
Tüker, M., Sınecen, M., & Mehmet Taha, E. S. E. R. (2026) · Scientific journal of Mehmet Akif Ersoy University. · doi:10.70030/sjmakeu.2033004
Füzesi, I., Lengyel, P., & Pancsira, J. (2026) · International Review of Applied Sciences and Engineering · doi:10.1556/1848.2026.01535
SAMP: source-aware multi-prototype learning for machine-generated text detection
Xu, Y., Yang, W., Yin, Y., Lv, H., Wang, Z., He, J., Jia, X., & Wang, X. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01331-z
Tamuka, N. (2026) · Discover Computing · doi:10.1007/s10791-026-10710-z
Kocagul, H. (2026) · Cankaya University Journal of Humanities and Social Sciences · doi:10.47777/cankujhss.1957142
KORKMAZ, Ş., Alkan, M., & Koçak, A. (2026) · Electronics · doi:10.3390/electronics15215108
- Authors
- Wang, Y., Mansurov, J., Ivanov, P., Su, J., Shelmanov, A., Tsvigun, A., Mohammed Afzal, O., Mahmoud, T., Puccetti, G., Arnold, T., Aji, A., Habash, N., Gurevych, I., & Nakov, P.
- Affiliations
- New York University Abu Dhabi (AE)
- Technische Universität Darmstadt (DE)
- Mohamed bin Zayed University of Artificial Intelligence (AE)
- ORCID
- Venue
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2024
- Pages
- 3964-3992
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W4402684031
- Cited by
- 25
- References
- 0
- Citations by year
- 2026: 7 · 2025: 14 · 2024: 4
- FWCI
- 7.38
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- AI-generated text detection, black-box detection, evaluation benchmark, text generation
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
