LLMs Making Finance Articles Less Readable?

How is the growing use of large language models (LLM) in production of academic papers in finance affecting outputs? In their June 2025 paper entitled “Certainly! Generative AI and its Impact on Academic Writing (in Finance)”, Thomas Walther and Marie Dutordoir investigate how use of LLMs has affected academic writing in finance, with focus on readability. They quantify readability via the widely-used Flesch- Kincaid Index (FKI) and Gunning-Fog Index (GFI), both of which estimate the number of years of education required to understand a certain text in a first reading. They also look at author characteristics associated with LLM use and the impact of LLM use on author publication quantity, quality (journal rankings) and impact (citations). They treat the release of ChatGPT at the end of November 2022 as the LLM adoption date. To determine author use of LLMs, they: (1) identify specific words that disproportionally appear in LLM-generated text (AI Words); (2) count the AI Words in the abstract, introduction and full text of each article; and, (3) divide the number of AI Words by the total number of words in the article. Using 41,489 articles (minimum 200 words) from 34 finance journals published in English from January 1, 2000 to April 1, 2025 (32,993 from before December 1, 2022 and 8,496 after), they find that: (more…)