Is ChatGPT Involved in Texts? Measure the Polish Ratio to Detect ChatGPT-Generated Text
Open accessThe DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
The remarkable capabilities of large-scale language models, such as ChatGPT, in text generation have impressed readers and spurred researchers to devise detectors to mitigate potential risks, including misinformation, phishing, and academic dishonesty. Despite this, most previous studies have been predominantly geared towards creating detectors that differentiate between purely ChatGPT-generated texts and human-authored texts. This approach, however, fails to work on discerning texts generated through human-machine collaboration, such as ChatGPT-polished texts. Addressing this gap, we introduce a novel dataset termed HPPT (ChatGPT-polished academic abstracts), facilitating the construction of more robust detectors. It diverges from extant corpora by comprising pairs of human-written and ChatGPT-polished abstracts instead of purely ChatGPT-generated texts. Additionally, we propose the "Polish Ratio" method, an innovative measure of the degree of modification made by ChatGPT compared to the original human-written text. It provides a mechanism to measure the degree of ChatGPT influence in the resulting text. Our experimental results show our proposed model has better robustness on the HPPT dataset and two existing datasets (HC3 and CDB). Furthermore, the "Polish Ratio" we proposed offers a more comprehensive explanation by quantifying the degree of ChatGPT involvement.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Yang et al. [36] constructed a novel dataset termed HPPT comprising pairs of human-written and ChatGPT-polished abstracts.Based on the sample pairs in the dataset, they proposed a new metric called Polish Ratio.It was used to quantify the extent of text modification before and after being revised with ChatGPT by calculating the Jaccard Distance and Levenshtein Distance between the sample pairs.A”
From Enhancing the Robustness of AI-Generated Text Detectors: A Survey (2025) · cites this paper as [36]
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
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., Wong, D. F., & Chao, L. S. (2023) · arXiv · doi:10.48550/arxiv.2310.14724 · Cited by 212
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
An explainable framework for assisting the detection of AI-generated textual content
Yan, S., Wang, Z., & Dobolyi, D. G. (2025) · Decision Support Systems · doi:10.1016/j.dss.2025.114498 · Cited by 17
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
Wang, J., Jairath, N. K., Shue, E., Perrotta, P. L., & Hu, G. (2025) · JAAD International · doi:10.1016/j.jdin.2025.05.013 · Cited by 9
Stack More LLM’s: Efficient Detection of Machine-Generated Texts via Perplexity Approximation
Gritsai, G., Khabutdinov, I., & Grabovoy, A. (2024) · Doklady Mathematics · doi:10.1134/s1064562424602075 · Cited by 9
A Method for Distinguishing Model Generated Text and Human Written Text
Shimada, H., & Kimura, M. (2024) · Journal of Advances in Information Technology · doi:10.12720/jait.15.6.714-722 · Cited by 5
Cheng, Z., Zhou, L., Jiang, F., Wang, B., & Li, H. (2025) · Proceedings of the ACM on Web Conference 2025 · doi:10.1145/3696410.3714770 · Cited by 3
Self-citationDetecting authorship between generative AI models and humans: a Burrows’s Delta approach
Zhu, H., & Lei, L. (2025) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqaf048 · Cited by 4
Bilingual generated text detection through semantic and statistical analysis
Min, C., Zhang, R., & Liu, J. (2025) · Intelligent Data Analysis · doi:10.1177/1088467x241307192 · Cited by 4
A Survey on AI-Generated Text Detection: Methods, Challenges, and Future Directions
Ismail, A. A., Ahmed, C., & ElKorany, A. (2025) · Future International Conference on Artificial Intelligence and Cybersecurity (FICAC) · doi:10.1109/ficac65757.2025.11341850 · Cited by 2
Determining Whether a Turkish Text is Produced by Artificial Intelligence or Human
Er, R. N., & ÇOĞALMIŞ, K. N. (2024) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi60790.2024.10585770
Highly generalizable cross-domain machine-generated text detection
Xing, Y., Men, Y., Luo, S., Yang, Z., Zhou, J., & Pan, L. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133426
Out of Order: On the Importance of Word Positions in Explaining Text Classification
Stockdiek, J. L., Britta, G., Griesbach, M., & Grimme, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21477-5_29
Perception of ChatGPT in University Students to Solve Mathematics Exercises
Bastidas-Chalán, R., Mantilla-Morales, G., Rentería-Torres, A., Valencia-Ordoñez, P., & Zambrano-Vera, E. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-22641-9_5
Lo, C., Wang, X., Liu, G., & Huang, G. (2026) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/10711813261493613
Metadata
- Authors
- Yang, L., Jiang, F., & Li, H.
- Affiliations
- Chinese University of Hong Kong (HK)
- University of Science and Technology of China (CN)
- ORCID
- Li, Haizhou
- Venue
- APSIPA Transactions on Signal and Information Processing
- Publisher
- Emerald
- Published
- 2024
- Volume
- 13
- Issue
- 2
- ISSN
- 2048-7703 (ISSN-L)
- OpenAlex
- W4391758837
- Cited by
- 16
- References
- 0
- Citations by year
- 2026: 4 · 2025: 8 · 2024: 3
- FWCI
- 2.22
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by-nc
- Locations
- APSIPA Transactions on Signal and Information Processing (publishedVersion, cc-by-nc)
- arXiv (Cornell University) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University) (cc-by)
- Funders
- Shenzhen Research Institute of Big Data
- Shenzhen Research Institute, City University of Hong Kong
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- ChatGPT, large language models, textual authenticity, AI-generated text detection
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.