🖥️ **Poor Alignment and Steerability of Large Language Models: Evidence from College Admission Essays**

"_We consistently find that both types of LLM-generated essays are linguistically distinct from human-authored essays, regardless of the specific model and analytical approach. Further, prompting a specific sociodemographic identity is remarkably ineffective in aligning the model with the linguistic patterns observed in human writing from this identity group._"

Lee, J. et al. (2025) 'Poor Alignment and Steerability of Large Language Models: Evidence from  College Admission Essays,' arXiv (Cornell University) [Preprint]. https://doi.org/10.48550/arxiv.2503.20062..

#AI #ArtificialIntelligence #Technology #Tech #LLM #Essays #ComputerScience #Research #Preprint #Academia #Academics