2 papers
cs.CL2026
Experimental evidence of progressive ChatGPT models self-convergence
Konstantinos F. Xylogiannopoulos, Petros Xanthopoulos, Panagiotis Karampelas +1
Large Language Models (LLMs) that undergo recursive training on synthetically generated data are susceptible to model collapse, a phenomenon marked by the generation of meaningless…
cs.CL2025
The power of text similarity in identifying AI-LLM paraphrased documents: The case of BBC news articles and ChatGPT
Konstantinos Xylogiannopoulos, Petros Xanthopoulos, Panagiotis Karampelas +1
Generative AI paraphrased text can be used for copyright infringement and the AI paraphrased content can deprive substantial revenue from original content creators. Despite this re…