AUTOMATED DETECTION OF TEXT GENERATED BY LARGE LANGUAGE MODELS
DOI:
https://doi.org/10.34132/mspc2025.01.14.01Keywords:
academic fraud, artificial intelligence, large language models, plagiarism detectors, text generation.Abstract
The theses present an analysis of the capabilities of modern detectors to detect text generated by large language models. In particular, the use of artificial intelligence for academic fraud is considered. The quality of the generated text is increasing, which makes plagiarism detection more difficult. Identification of generated papers and reports in the field of education has some differences compared to other areas, mainly due to the specificity and contextual nature of educational tasks. Currently there are many instruments developed for detecting generated text. A modern detector should be reliable in recognizing such texts to prevent the misuse of artificial intelligence.
References
Foltynek, T., Meuschke, N., & Gipp, B. (2019). Academic plagiarism detection: a systematic literature review. ACM Computing Surveys (CSUR), 52(6), pp. 1-42. URL: https://doi.org/10.1145/3345317
Mitchell, E., Lee, Y., Khazatsky, A., Manning, C.D., & Finn, C. (2023). DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature. International Conference on Machine Learning. URL: https://doi.org/10.48550/arXiv.2301.11305
Hu, X., Chen, P., & Ho, T. (2023). RADAR: Robust AI-Text Detection via Adversarial Learning. URL: https://doi.org/10.48550/arXiv.2307.03838
Verma, V. K., Fleisig, E., Tomlin, N., & Klein, D. (2023). Ghostbuster: Detecting Text Ghostwritten by Large Language Models. North American Chapter of the Association for Computational Linguistics. URL: https://doi.org/10.48550/arXiv.2305.15047
Chen, Y., Kang, H., Zhai, V., Li, L., Singh, R., & Ramakrishnan, B. (2023). GPT-Sentinel: Distinguishing Human and ChatGPT Generated Content. URL: https://doi.org/10.48550/arXiv.2305.07969
Tang, R., Chuang, Y., & Hu, X. (2023). The Science of Detecting LLM-Generated Text. Communications of the ACM, 67, 50-59. URL: https://doi.org/10.48550/arXiv.2303.07205
Liang, W., Yuksekgonul, M., Mao, Y., Wu, E., & Zou, J.Y. (2023). GPT detectors are biased against non-native English writers. Patterns, 4. DOI: https://doi.org/10.48550/arXiv.2304.02819
