CHEAT: A Large-Scale Dataset for Detecting CHatGPT-writtEn AbsTracts
Open accessThe DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Abstract
The powerful ability of ChatGPT has caused widespread concern in the academic community. Malicious users could synthesize dummy academic content through ChatGPT, which is extremely harmful to academic rigor and originality. The need to develop ChatGPT-written content detection algorithms calls for large-scale datasets. In this paper, we initially investigate the possible negative impact of ChatGPT on academia, and present a large-scale CHatGPT-writtEn AbsTract dataset (CHEAT) to support the development of detection algorithms. In particular, the ChatGPT-written abstract dataset contains 35,304 synthetic abstracts, with$Generation$,$Polish$, and$Fusion$as prominent representatives. Based on these data, we perform a thorough analysis of the existing text synthesis detection algorithms. We show that ChatGPT-written abstracts are detectable with well-trained detectors, while the detection difficulty increases with more human guidance involved.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019) · arXiv · doi:10.48550/arxiv.1910.01108 · Cited by 4,653
Training Language Models to Follow Instructions with Human Feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-2011 · Cited by 3,117
Domain-specific language model pretraining for biomedical natural language processing
Gu, Y., Tinn, R., Cheng, H., Lucas, M., Usuyama, N., Liu, X., Naumann, T., Gao, J., & Poon, H. (2022) · ACM Transactions on Computing for Healthcare · doi:10.1145/3458754 · Cited by 2,170
ChatGPT is fun, but not an author
Thorp, H. H. (2023) · Science · doi:10.1126/science.adg7879 · Cited by 1,437
How Multilingual is Multilingual BERT?
Pires, T., Schlinger, E., & Garrette, D. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1493 · Cited by 1,351
Gao, C. A., Howard, F. M., Markov, N. S., Dyer, E. C., Ramesh, S., Luo, Y., & Pearson, A. T. (2022) · doi:10.1101/2022.12.23.521610 · Cited by 1,099
Gao, C. A., Howard, F. M., Markov, N. S., Dyer, E. C., Ramesh, S., Luo, Y., & Pearson, A. T. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00819-6 · Cited by 1,099
NLTK: The Natural Language Toolkit
Bird, S. (2006) · Proceedings of the COLING/ACL on Interactive presentation sessions - · doi:10.3115/1225403.1225421 · Cited by 841 · cited 1×
“In this part, we use the POS module in NLTK [36] to calculate the lexical distributions of abstract texts in the CHEAT dataset, and sort them by lexical percentage.”
GPT detectors are biased against non-native English writers
Liang, W., Yuksekgonul, M., Mao, Y., Wu, E., & Zou, J. (2023) · Patterns · doi:10.1016/j.patter.2023.100779 · Cited by 673 · cited 1×
“(cid:2) ChatGPT-essay : The ChatGPT-essay dataset [26] contains 303 human-written paragraphs and 443 ChatGPT-generated paragraphs.”
Defending Against Neural Fake News
Zellers, R., Holtzman, A., Rashkin, H., Bisk, Y., Farhadi, A., Roesner, F., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1905.12616 · Cited by 569
GLTR: Statistical Detection and Visualization of Generated Text
Gehrmann, S., Strobelt, H., & Rush, A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.18653/v1/p19-3019 · Cited by 470 · cited 2×
“The visualization results are obtained using GLTR [7].”
GLTR: Statistical Detection and Visualization of Generated Text
Gehrmann, S., Strobelt, H., & Rush, A. M. (2019) · arXiv · doi:10.48550/arxiv.1906.04043 · Cited by 460
Release Strategies and the Social Impacts of Language Models
Solaiman, I., Brundage, M., Clark, J., Askell, A., Herbert-Voss, A., Wu, J., Radford, A., Krueger, G., Kim, J. W., Kreps, S., et al. (2019) · arXiv · doi:10.48550/arxiv.1908.09203 · Cited by 292 · cited 3×
“(cid:2) OpenAI-detector The detector [22] is officially provided by OpenAI.”
ChatGPT and Software Testing Education: Promises & Perils
Jalil, S., Rafi, S., LaToza, T. D., Moran, K., & Lam, W. (2023) · 2023 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW) · doi:10.1109/icstw58534.2023.00078 · Cited by 270 · cited 1×
“(cid:2) CST : The ChatGPT-software-testing dataset [27] includes ChatGPT’s answers to 31 questions from the software testing book named “Introduction to Software Testing 2nd Edition”.”
Automatic Detection of Generated Text is Easiest when Humans are Fooled
Ippolito, D., Duckworth, D., Callison-Burch, C., & Eck, D. (2019) · arXiv · doi:10.48550/arxiv.1911.00650 · Cited by 264 · cited 1×
“After that, Ippolito et al. [24] constructed a novel text synthesis dataset and fine-tuned the BERT classification model, significantly improving the detection accuracy on synthetic texts.”
Automatic Detection of Generated Text is Easiest when Humans are Fooled
Ippolito, D., Duckworth, D., Callison-Burch, C., & Eck, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.164 · Cited by 264 · cited 1×
“After that, Ippolito et al. [24] constructed a novel text synthesis dataset and fine-tuned the BERT classification model, significantly improving the detection accuracy on synthetic texts.”
Is Chatgpt a menace for creative writing ability? An experiment
Niloy, A. C., Akter, S., Sultana, N., Sultana, J., & Rahman, S. I. U. (2024) · Journal of Computer Assisted Learning · doi:10.1111/jcal.12929 · Cited by 198
Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study
Cao, Y., Zhou, L., Lee, S., Cabello, L., Chen, M., & Hershcovich, D. (2023) · Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP) · doi:10.18653/v1/2023.c3nlp-1.7 · Cited by 163
Will ChatGPT Get You Caught? Rethinking of Plagiarism Detection
Khalil, M., & Er, E. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-34411-4_32 · Cited by 146
Feature-based detection of automated language models: tackling GPT-2, GPT-3 and Grover
Fröhling, L., & Zubiaga, A. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.443 · Cited by 106
Cited by
A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4
Kalyan, K. S. (2024) · Natural Language Processing Journal · doi:10.1016/j.nlp.2023.100048 · Cited by 335
A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
Wu, J., Yang, S., Zhan, R., Yuan, Y., Chao, L. S., & Wong, D. F. (2025) · Computational Linguistics · doi:10.1162/coli_a_00549 · Cited by 212
A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
Wu, J., Yang, S., Zhan, R., Yuan, Y., Wong, D. F., & Chao, L. S. (2023) · arXiv · doi:10.48550/arxiv.2310.14724 · Cited by 212
“In essence, the consequences of LLM-generated text encompass both societal [27] and academic [28] risks, and the use of LLM-generated data will hinder the future development of LLMs and detection technology.”
BackgroundDeepfake: definitions, performance metrics and standards, datasets, and a meta-review
Altuncu, E., Franqueira, V. N. L., & Li, S. (2024) · Frontiers in Big Data · doi:10.3389/fdata.2024.1400024 · Cited by 134
Veselovsky, V., Ribeiro, M. H., & West, R. (2023) · arXiv · doi:10.48550/arxiv.2306.07899 · Cited by 73
“These concerns have led to work on watermarking LLM output (Kirchenbauer et al., 2023) by slightly altering the odds of each token during sampling, and to further work on methods for improving the detection of synthetically generated text (Yu et al., 2023; Verma et al., 2023; Diwan et al., 2021).”
Metadata
- Authors
- Yu, P., Chen, J., Feng, X., & Xia, Z.
- Venue
- IEEE Transactions on Big Data
- Published
- 2025-06
- Volume
- 11
- Issue
- 3
- Pages
- 898-906
- ISSN
- 2332-7790 (ISSN-L)
- 2372-2096
- OpenAlex
- W4406983030
- Cited by
- 42
- References
- 22
- FWCI
- 13.73
- Type
- journal article
- Language
- en
- Open access
- green
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.