%0 Generic %1 gray2024chatgpt %A Gray, Andrew %D 2024 %K ChatGPT academic_publishing artificial_intelligence large_language_models scholarly_literature %R 10.48550/arXiv.2403.16887 %T ChatGPT "contamination": estimating the prevalence of LLMs in the scholarly literature %U https://arxiv.org/abs/2403.16887 %X The use of ChatGPT and similar Large Language Model (LLM) tools in scholarly communication and academic publishing has been widely discussed since they became easily accessible to a general audience in late 2022. This study uses keywords known to be disproportionately present in LLM-generated text to provide an overall estimate for the prevalence of LLM-assisted writing in the scholarly literature. For the publishing year 2023, it is found that several of those keywords show a distinctive and disproportionate increase in their prevalence, individually and in combination. It is estimated that at least 60,000 papers (slightly over 1% of all articles) were LLM-assisted, though this number could be extended and refined by analysis of other characteristics of the papers or by identification of further indicative keywords.

@misc{gray2024chatgpt, abstract = {The use of ChatGPT and similar Large Language Model (LLM) tools in scholarly communication and academic publishing has been widely discussed since they became easily accessible to a general audience in late 2022. This study uses keywords known to be disproportionately present in LLM-generated text to provide an overall estimate for the prevalence of LLM-assisted writing in the scholarly literature. For the publishing year 2023, it is found that several of those keywords show a distinctive and disproportionate increase in their prevalence, individually and in combination. It is estimated that at least 60,000 papers (slightly over 1% of all articles) were LLM-assisted, though this number could be extended and refined by analysis of other characteristics of the papers or by identification of further indicative keywords. }, added-at = {2024-03-26T15:49:35.000+0100}, archiveprefix = {arXiv}, author = {Gray, Andrew}, biburl = {https://www.bibsonomy.org/bibtex/2174296b0b70bc4239b5cf485c7d8386d/meneteqel}, doi = {10.48550/arXiv.2403.16887}, eprint = {2403.16887}, interhash = {2046d37457a2646b3322198bb6245d3e}, intrahash = {174296b0b70bc4239b5cf485c7d8386d}, keywords = {ChatGPT academic_publishing artificial_intelligence large_language_models scholarly_literature}, language = {en}, month = mar, primaryclass = {cs.DL}, timestamp = {2024-03-26T15:49:35.000+0100}, title = {ChatGPT "contamination": estimating the prevalence of LLMs in the scholarly literature}, url = {https://arxiv.org/abs/2403.16887}, year = 2024 }