A recent study published on arXiv explored the differences between essays written by students and those generated by large language models (LLMs) using a Korean writing rubric. The research found that LLM-generated essays significantly outperformed student essays, scoring an average of 18.35 points higher. Key factors contributing to this gap were orthographic norms and genre-appropriate register, where LLMs consistently achieved maximum scores. While LLMs excelled in these areas, human readers found student essays stronger in creativity and natural phrasing, indicating areas where human writing still holds an advantage. AI
IMPACT Highlights LLMs' current strengths in formal writing aspects, potentially influencing educational assessment strategies.
RANK_REASON Academic paper detailing research findings on LLM writing capabilities. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
