Work

Study on comparative and discriminatory methodology of human and machine-generated languages

Year: 2026

Type: article

Abstract: The discrimination of large language models (LLMs) against humans is an emerging issue in the real-world application of LLMs.The hallucination and collapse phenomenon is a crucial problem.The starting point for addressing these problems is to discriminate between human and machine texts.In this paper, we investigate the data construction, statistical analysis, including Latent Dirichlet Allocation (LDA), for the features, and the construction of the classifier.Through this process, we validate the possibility of certain features that are useful in discriminating the source of LLMs.We can construct a more elaborate classifier for discriminating between humans and LLMs, and furthermore, various LLMs.It can contribute to classifying the various LLMs and detecting their usage and their behaviors.

Source: Korean Journal of Applied Statistics

DOI: 10.5351/kjas.2026.39.3.235

Authors: Hyungbin Park, Shinsung Kang, Kihoon Lee, Gwangsu Kim

Institution: Jeonbuk National University

Language: English

Topic: Authorship Attribution and Profiling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funders: National Research Foundation, Ministry of Education, National Research Foundation of Korea, Jeonbuk National University

Awards: G211153518, G2940152539