Large Language Models for Career Readiness Prediction

Large Language Models (LLMs) have recently achieved state-of-the-art performance on many benchmark Natural Language Processing (NLP) tasks. In this work, we are introducing a novel application, career readiness prediction, in the area of NLP for education. We analyze a dataset of student narratives and explore how reliably different LLMs classify them using Marcia's (1980) identity statuses. We explore the capabilities and limitations of LLMs on this new task and find that there is good potential for automated career readiness evaluation, and for improved survey design that enables larger-scale data collection.